Save hours in your job search with Python and GPT
Skip straight to the bottom if you only want to know how to save hours of work in your job searching process just by using two simple python scripts + GPT As a former startup founder, lately I've been facing the complex challenge of transitioning back into the traditional job market. With no experience in the job searching game for the last 10+ years, I had no idea what I was getting myself into I still have a lot to go, but one of the most annoying and time-consuming parts of the process of applying to jobs so far, has been just even trying to find the right jobs to apply to Every jobs site…
What it does
In the maker’s words, at launch
Skip straight to the bottom if you only want to know how to save hours of work in your job searching process just by using two simple python scripts + GPT As a former startup founder, lately I've been facing the complex challenge of transitioning back into the traditional job market. With no experience in the job searching game for the last 10+ years, I had no idea what I was getting myself into I still have a lot to go, but one of the most annoying and time-consuming parts of the process of applying to jobs so far, has been just even trying to find the right jobs to apply to Every jobs site has hundreds or thousands of jobs, they are usually hard to filter. Then when you get the results, you still have to spend a lot of time reading and scrolling through the listings, figuring out which ones are good matches and which ones are not Even here in HN, every "Ask HN: Who is hiring?" post has hundreds of listings (the February one has 300+ job posts). Reading through them all can take hours, which is super draining. By the time you are done reading, you are almost out of energy, and you haven't even started applying yet I just wished I had a database where I could do something like: SELECT summary, why_is_a_good_fit, how to apply, link FROM hn_jobs WHERE remote AND use_ruby AND good_fit So, I built it. Well, I wrote a couple of python scripts that: * scrape an "Ask HN: Who is hiring?" post * processes all the listings with GPT * saves all the data in a sqlite3 db It takes a few minutes to run the whole thing and populate the db (for each listing, a prompt is sent to GPT with questions, a resume and the job listing, GPT returns a json object with answers that get stored in the db) But after it's done, I can get the absolute best matches for my own resume in seconds With each result, I get the information about the listing, as well as why it is a good fit for me and instructions on how to apply (including link and or email address) So far I've probably put more time into this than I've saved (surely there's an XKCD comic about this), but hopefully this hasn't been in vain and my loss can be your gain. That's why below I'm sharing links to the scripts. Please feel free to check them out, use them and modify them to fit your own needs There is a lot of space for improvement, especially building and tweaking the prompt, which is one of the most challenging things to iterate on. If you try the scripts, make sure to modify the included sample resume, the questions asked and checking that the sample json output structure matches your questions -> Would love to hear your feedback, suggestions, and also stories about your recent job searching experience in tech! Thank you Links to scripts: * get_ask_hn_jobs.py: gets job listings from HN (make sure to adjust the base url of the "Ask HN: Who is hiring?" page to scrape) - run this first to populate your local db - https://gist.github.com/nicobrenner/88cc2aaf4fde7cbb119c6ca67fd50bc2 * ask_gpt_job_listings.py: enriches jobs listings from db using GPT (you need to add your own OpenAI API key, make sure to modify these variables: resume, roles, ideal_job_questions, prompt, and also check that the sample structure of output_format matches your prompt/questions) - run this after running get_ask_hn_jobs.py - https://gist.github.com/nicobrenner/dc1e6968dcd396c6367a63ac4c61f5d3 * filtered_job_listings.sql: query for sqlite3 db that gets best job listing matches - you should tweak the query to filter according to your preferences - https://gist.github.com/nicobrenner/f8da15c99c45c229c03c89dae1ed94d6
Does the same job
all alternatives →- AIAn IRC channel to help people find jobs2014 · ▲23
I had an idea a couple days ago and I went with it. Basically, the idea was to create an IRC channel to help people find jobs; computer related jobs, in particular. There would be a bot to display job listings. So I started working on a first take on the bot. I decided to use Python because I love the language and I wanted to get more experience with a its libraries. TwitterBot (or JobFeeder on ##jobfeed) as I call it, uses Twisted (https://pypi.python.org/pypi/Twisted) and Twitter (https://pypi.python.org/pypi/twitter)for now. Basically, it gets the…
- PDPython Developer Job Board2019 · ▲26
Today I release my 3. Job Board, running on my product https://www.boardengine.io, for Python Developers: https://pythonjob.xyz
- AJAPI Jobs, a new job site focused on APIs2012 · ▲37
In my spare time to remind myself that I could actually build stuff (and learn some Python, Flask, Redis, etc) I put together a simple job board to feature the best jobs in the API industry. The jobs can be either building APIs at companies like Twilio, Box, Stripe, etc. or integrating them. In addition to featuring those jobs, I'm also aggregating API jobs from GitHub Jobs, Stack Overflow Careers 2.0, and 37signals Job Board. Today I launched with what I would consider an 'MVP' with jobs from SendGrid, TokBox, Twilio, Zencoder, Parse, Stripe, Pusher and Box. Check it out, I'd love to know…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, February 2024
the whole month →
MarketingIdeas.com▲1,230Never run out of marketing ideas ever again
Growth · 2024 · marketingideas.com
