Image: a typical resume content extraction workflow from neurond.com

I used to keep my résumé (from here, “resume”) very up-to-date. For a long time, I had a resume crafted in #LaTeX because I have a long history with using that typesetting and markup language for purposes other than the ones most people think of, e.g. I wrote my college English papers in it, I had a slew of templates I created while I was a practicing attorney that would create letters, motions, and envelopes from source .tex files, etc. Keeping content in text makes it more portable across platforms and applications, and the nature of Microsoft Word is that you need to fully re-create the resume every couple years because some invisible formatting munges the entire document.

TL;DR I ended up using RenderCV as mentioned below in the [[Resume Workflow#RenderCV|RenderCV section]].

In the time since I last relied upon a resume, the method of applying for jobs –and more importantly, how recruiters review submissions– has changed pretty drastically. And despite all the great advances in technology over the past ten years, apparently, HR systems still are not that great at parsing a PDF or Word doc into text that can be machine-read by whatever algorithms and/or AI they’re using to perform the first pass. Because of this, you want to make sure to submit a machine-friendly description of your experience. There really should be a standard for all this stuff that makes it easy on both the applicant and the hiring manager. Like, I don’t know, some sort of HR standards body or something. A standard has never emerged, and I suspect that LinkedIn has a lot to do with that.

Additionally, having an easy way to keep one’s resume in sync and in multiple formats means that it can be quickly used for many purposes, from printing an attractive hard copy to piping it through some [[Fabric]] AI workflows. So this set me on a fairly long hunt for a system where I could write once, and generate in multiple formats.

The search for a resume workflow

First round

LaTeX & Pandoc

Since my resume was already in LaTeX, using the 20 second CV set of template –which I think is very nice– I went and updated that and then ran it through pandoc, which is a multi-format document converter. The results ended up being pretty poor and not useful. The PDF looked great, obviously, but pandoc did not understand the LaTeX very well and the Markdown required a lot of edits.

We want everything to look good upon compilation/export/save as/whatever, so this was not an option.

Interlude

I had kind of given up at this point, figuring I either needed to just go Google Docs or maintain a Markdown version and attempt to keep them in sync. Then, I came across a post about an auto-application bot and the author had a related project that used resume information formatted as YAML to create a specific resume based upon job description or LinkedIn post.

Resume from Job Description

This project is called resume render from job description (no cute animal names or obtuse references in this project!), and I gave it a try, but it appeared to require all the fields, including e.g. GPA. I don’t know about you, but I'm way past the point in my career where I'm putting my GPA on a resume, so it wasn’t that useful.

It was late on a Thursday night, so obviously it was time to look a bit further into the rabbit hole

Online options

I found a number of projects that were a service model where they host and render the resume for you. These included resume.lol (I question the naming choice here), Reactive resume (opensource, excellent domain name, and it has nice documentation), and WTF resume (my thought exactly!).

These all came from a post of 14 Open-source Free Resume Builder and CV Generator Apps.

JSONResume

As I traveled further down the Internet search rabbit hole, I came across JSON Resume, an #opensource project with a hosting component where people craft their resumes in JSON and it can then render in a number of formats either via a command-line tool or within their hosted service, making it a kind of hybrid option.

At this point, I felt like I was almost there, but it wasn’t exactly what I wanted. JSONResume is very focused around being part of their ecosystem and publishing within their hosting ecosystem. The original #CLI tool is no longer maintained, and a new one is being worked on, which appears minimal but sufficient for the task. A nice thing is that they have some add-ons and have created a sort of ecosystem of tools. Looking over the project’s 10 year history, those tools have a tendency to come and go, but such is the nature of OSS.

The Award for “Project Most Suited to My Workflow” goes to….

Another great thing about JSON Resume is that they, i.e. Thomas Davis, have done a fantastic job of cataloging various resume systems out there in their JSON Resume projects section. There is so much interesting stuff here –and a lot of duplicative effort ahem see the “HR Standards” comment above– that you can spend a couple days looking for the project that best fits your needs. For me, I landed on RenderCV, which is not only in the bibliography, but also mentioned on the Getting Started page because there are tools to leverage JSON Resume from RenderCV!

So without further ado…

RenderCV

While RenderCV is a part of the JSON Resume ecosystem, in that people have created scripts to convert from the latter to the former, it is a completely separate and standalone project. Written in #python and installable via pip. RenderCV’s approach is to leverage a YAML file, and from that generate consistent resumes in PDF, HTTML, Markdown, and even individual PNG files, allowing the applicant to meet whatever arcane requirements the prospective employer has.

graph LR

	YAML --> TeX & Markdown 
	TeX --> PDF & HTML & PNG

Resume generation workflow

Using RenderCV

Getting started with RenderCV is like pretty much any other project built in python

1. Create a virtual environment using venv or conda, e.g. conda create -n renderCV python=3.12.4
2. Install via pip with a simple command pip install rendercv
3. Follow the quick start guide and create a YAML file with your information in it
4. Run rendercv render <my_cv>.yaml
5. View the lovely rendered résumé

Extending RenderCV

This was great, as I now have a very easy-to-edit source document for my résumé and can quickly create others. I’m hoping Sina, the author, makes the framework a bit more extensible in the future because the current templates are oriented toward people with STEM backgrounds looking for individual contributor roles. However, as some of us move further in our careers, the résumé should be less about skills and projects, but more about responsibilities and accomplishments as we lead teams. I have enhanced the “classic” and “sb2nov” themes so that they take these keywords as subsections to a specific company/role combination under the professional_experience section.

Theme update for Leaders and Managers

I created a fork which contains updates to v1.14, adding the “Responsibilities” and “Accomplishments” subsections for company: under the Experience section.
This allows leaders to craft their resume or CV in such a way that it highlights the breadth of their influence and impact to the organization.

The following themes support the additional subsections: – markdown – classic – sb2nov

A non-updated theme will simply ignore the content under these subsections; omitting these sections will make the resume look like the original theme. Hopefully the framework will be more extensible in the future and I can add this as a pull request.
In the meantime, the forked repo at https://github.com/ktneely/rendercv4leaders should work on its own, or the /ExperienceEntry.j2.tex and /ExperienceEntry.j2.md files from those themes can simply be copied over the existing.

How to use

Usage is extremely straightforward, as this merely extends the framework with a couple new keywords for the Experience section and looking for a preceding company declaration. Here is an example:

professional_experience:
  - company: NASA
	position: Director of Flight Operations
	location: Houston, TX
	start_date: 1957-03
	end_date: 1964-06
	responsibilities:
	  - Manage the Control room.
	  - Write performance reports.
	  - Smoke copious amounts of cigarettes
	accomplishments:
	  - 100% staff retention over the course of 9 rocket launches.
	  - Mobilized and orchestrated multiple teams to rescue astronauts trapped in space.
	  - Lung cancer.

This will then render “responsibilities” and “accomplishments” as italicized sections under the job role, highlighting what a difference made while performing in that role.

Maintaining Multiple Versions

This is basically what it all comes down to: the ability to maintain different versions for your target companies. While some work is being done to modularize the source content, it is not yet to the point where each section of the resume is a building block that can be invoked at compile time. What I do is maintain different YAML files and use the parameters in the rendercv_settings section to direct the output to different, meaningfully-named directories while maintaining a generic name for the file itself.

So, instead of “Kevin-LargeCorprole.pdf”, “Kevin-Startuprole.pdf”, etc., I simply send “Kevin-CV.pdf”. This way, it’s not incredibly obvious to the reviewer that I have specially-crafted a resume for that job, it just happens to look like I have exactly what they’re looking for in my default resume.

Automation

Want to automate the build of your resume whenever you update the source file(s)? Look no further than rendercv pipeline to generate the output whenever you commit source to GitHub.

Also, since version 1.15, the --watch flag will watch the source file locally and re-compile every time you save the source YAML file.

References and further exploration

1. Neurond.com blog post: What is a CV/Resume Parser and How Does it Work?, Trinh Nguyen, Aug 16, 2022.
2. TeXMaker: an Open-source TeX editor
3. RenderCV user guide

Creating a Michelin menu with Generative AI

We've been watching season three of The Bear and it is totally nuts, filled with drama and psychology, and human relationships, and –when they can get around to it– cooking food. This is a fantastic series, and as foodies, you can imagine that my wife and I really enjoy it. The series is intense, following a classically-trained, at the top of his game chef as he “drops down” from a fancy restaurant to a steak sandwich shop and works back toward where he was before.

That’s not a spoiler, it’s the premise. And this isn’t a review, it was just something in my mind as I experimented with this new tool called LobeChat, which is an interface to #genAI inference servers such as #OpenAI’s #chatGPT, #Claude, and nearly any other commercial or #opensource system you can imagine. I'm tweaking a #homelab hosted genAI inference server and this post is about experimenting with [Ollama]() and a Lobe chat front end for easy access. I haven’t formed a final opinion on this setup at this time, but the #LobeChat front end allows for the quick switching between inference servers and their hosted models. While not being super easy to configure, once it works, the whole thing looks very easy for someone, i.e. a roommate or a spouse, to flip between models -even in the same conversation.

So let’s look at some results. Of course, the results are about the models themselves, but the point here is that LobeChat made it easy to switch between them as I continued to develop the conversation.

First prompt

This was with ChatGPT (4o, I think). I needed something to test that an integration was working. We had just watched The Bear so this is what I came up with:

as fast as you can, what's the best restaurant dinner menu with wine pairing that could win a Michelin 3 star award?

Response

Crafting a Michelin 3-star worthy dinner menu with wine pairings involves high-quality ingredients, exquisite preparation, and a thoughtful combination of flavors. Here’s a conceptual menu that could impress:

Amuse-Bouche: – Oyster with Champagne Foam – Wine Pairing: Champagne Brut

Appetizer: – Seared Scallops with Cauliflower Puree and Caviar – Wine Pairing: Chablis, Premier Cru

Soup: – Cream of White Asparagus with Truffle Oil – Wine Pairing: Viognier

Fish Course: – Poached Turbot with Fennel and Citrus Beurre Blanc – Wine Pairing: Pouilly-Fumé

Main Course: – Roasted Duck Breast with Plum Sauce, Parsnip Mash, and Seasonal Vegetables – Wine Pairing: Pinot Noir, preferably from Burgundy

Cheese Course: – A Selection of Artisan Cheeses with Honeycomb – Wine Pairing: Vintage Port

Dessert: – Chocolate Lava Cake with Raspberry Coulis and Homemade Vanilla Bean Ice Cream – Wine Pairing: Recioto della Valpolicella

Mignardises: – Petit Fours and Truffles

This menu balances rich flavors with delicate preparation, offering a progression of dishes that showcase both technique and creativity. Each wine pairing is chosen to enhance the flavors of the dishes, aiming to create a harmonious dining experience that could captivate both critics and diners alike.

Review

Not a bad first response, especially since I was just checking to see if the system worked.

Prompt 2: Get ChatGPT to refine it

That was pretty boring. I’m thinking early 90s fancy dining at best, but I wasn’t eating fancy back then and assume it was all shoulder pads, tuna steaks, and cocaine. Continuing with ChatGPT, I posed the following in an attempt to refine our menu (in retrospect, I was generous with the stars):

That's an incredibly boring menu. At best 2 stars. And that's in a region that is not known for its gastronomical excellence

Response

Creating a truly innovative and Michelin 3-star worthy menu certainly demands a more avant-garde approach, pushing culinary boundaries with unique combinations and exceptional techniques. Let's elevate the original concept to something more daring and creative:

Amuse-Bouche: – Nitro-frozen Lime and Ginger Pearls with Micro Basil – Wine Pairing: Small-batch Sake

First Course: – King Crab Tartare with Avocado Mousse, Mango Gel, and Edible Flowers – Wine Pairing: Albariño

Second Course: – Foie Gras Au Torchon with Saffron Pear Compote and Brioche Crisp – Wine Pairing: Sauternes

Fish Course: – Butter-Poached Monkfish with Leek Ash, Sea Beans, and a Lemon Verbena Emulsion – Wine Pairing: White Burgundy

Intermezzo: – Cucumber and Elderflower Sorbet

Main Course: – Sous-vide Venison Loin with Black Garlic Purée, Wild Mushrooms, and a Juniper Berry Reduction – Wine Pairing: Barolo

Cheese Course: – A Selection of Aged Cheeses with a Fig and Walnut Tapenade – Wine Pairing: Aged Madeira

Dessert: – Deconstructed Passion Fruit Tart with Coconut Foam, Crystallized Ginger, and Meringue Shards – Wine Pairing: Late Harvest Riesling

Petit Fours: – Matcha Green Tea Macarons, Raspberry Pâte de Fruit

This revised menu introduces more complex techniques and unusual ingredients, aiming to surprise and delight with every course. Wine pairings are carefully selected to complement and enhance these adventurous flavors, providing a sophisticated and memorable dining experience.

Review

Not bad! It would be nice if the wines were more than broad regions, however, I do appreciate the ‘ñ’ in Albariño. There’s nothing particularly innovative here; the fancy-sounding “Foie Gras Au Torchon with Saffron Pear Compote and Brioche Crisp” is a Thomas Keller recipe, so at least we’re pulling from the top now that I asked it to up its game.

Prompt 3: Let's try a different model

Not only am I using a different model at this point, llama3:instruct, but I am going to specify a food critic in order to change the menu.

Prompt

One more try: let's make a menu that would knock even James Beard out of his chair because it's so good

Response

You are absolutely right! That menu, while technically sound, lacks the daring, innovation, and personal touch needed to truly impress Michelin inspectors and earn those coveted three stars. It plays it too safe, relying on classic pairings and predictable dishes.

To push towards that 3-star level, we need to think outside the box:

• Ingredient Focus: Instead of “seasonal vegetables,” source hyper-local, unique produce with a story. Maybe a heirloom tomato variety grown in volcanic soil, or foraged mushrooms with a distinct flavor profile.
• Deconstruction & Fusion: Take classic elements and reimagine them. A deconstructed apple pie might involve caramelized apple spheres, crumble as a powder, and a cider foam. Fusion could bring Japanese umami to the duck dish, or Indian spices to the scallops.
• Unexpected Textures: Play with contrasts – crunchy, creamy, smooth, airy. Think smoked paprika meringue alongside the chocolate lava cake, or a black truffle “soil” under the turbot.

Wine Pairings Should Be Equally Bold: * Instead of a basic Chablis, consider an obscure producer from the Côte de Beaune known for mineral-driven wines.
* The Pinot Noir could be a lesser-known region with unique terroir, like Slovenia's Primorska. * Experiment with natural wines, or even sake pairings that complement specific dishes.

The Presentation Matters:

Plating should be artistic, telling a story through the arrangement of colors, textures, and shapes. It’s about creating an immersive experience for the diner.

A Michelin-worthy menu isn't just about taste; it's about pushing boundaries, showcasing creativity, and offering a truly unforgettable journey through flavor.

Review

This is less of a menu than some advice for the aspiring chef. Let’s try something different.

Prompt 4: Let's go for Three Stars!

I felt like this was the time to go for the gusto, let's see how a different model would respond, but also with all the history behind it.

Prompt

I asked: > One more try: let's make a menu that would knock even James Beard out of his chair because it's so good

While it's not a crazily-innovative menu, it has some classic touches of a what an American, Michelin-starred menu would look like, and

Response with gemma2

You want to blow James Beard away? This isn't about ingredients, it's about experience.

The Menu: A Symphony in Five Acts

• Act I: Awakening – Smoked Salmon “Caviar” with Beetroot Foam, Rye Crisp, and a single drop of Ossetra Caviar.

  • Pairing: Dry Riesling from Germany's Mosel Valley, expressing its slate minerality alongside the salmon's richness.

• Act II: Earth & Sky – Roasted Quail “Confit” with Black Truffle Jus, Heirloom Carrot “Clouds,” and a dusting of Micro Thyme.

  • Pairing: Oregon Pinot Noir, showcasing earthy notes that harmonize with the truffle while its bright acidity cuts through the richness.

• Act III: Fire's Dance – Charred Octopus with Smoked Paprika Aioli, Caramelized Onion Jam, and a drizzle of Chili Infused Olive Oil.

  • Pairing: Spanish Albariño, crisp and mineral-driven, its citrus notes complementing the octopus while balancing the smoky paprika.

• Act IV: Ocean's Bounty – Pan-Seared Sea Scallops with Saffron Risotto “Foam,” Dulse Crisp, and a single Pearl Oyster.

  • Pairing: Chablis Premier Cru, its intense minerality mirroring the scallops' brininess, while subtle citrus notes elevate the saffron risotto.

• Act V: Sweet Serenade – Deconstructed Peach Cobbler with Lavender Honey Ice Cream, Toasted Almond Brittle, and a hint of Rosemary Extract.

  • Pairing: Late Harvest Gewürztraminer from Alsace, its floral aroma echoing the lavender, while its sweetness complements the peach cobbler's richness.

The Experience:

• Each course is plated as a miniature work of art, using contrasting colors, textures, and temperatures.
• The dining room itself is a sensory experience, with soft lighting, calming music, and subtle aromas that enhance each dish.
• Service is impeccable, with knowledgeable staff guiding guests through the tasting menu and explaining the inspiration behind each course.

This is not just food; it's a journey for the senses, a story told through flavor and texture, leaving James Beard speechless (and perhaps, slightly envious).

Review

Wow, what a different response! This one could actually be a menu, with the wines having robust and specific descriptions. I especially like how the wines are sourced from all over the globe, really picking best of breed in the selections. As good as the wines are, however, the food does not look 3-star level to me. The dishes sound really nice, and there’s a fair bit of molecular gastronomy in there. However, aside from the poetic nature of the menu, I’m not sure this is a top-tier menu for a chef to execute.

Still, most of these items are good enough for a fake restaurant. If this was to show up in a video game or a novel, I think most people would accept it and move on.