Pennylane | Machine Learning Manager | Remote or Hybrid from Paris | Full-time
We aim to become the most beloved financial Operating System of French SMEs and Accounting Firms (and soon, European ones). We help entrepreneurs rid themselves of time-consuming tasks related to accounting and finance while providing them with access to key financial information to assist in making the best decisions for their business.
Machine Learning is core to the most-loved features in our products. The ML team is growing and we are hiring a second ML Manager.
As a Machine Learning Manager, you will lead a team of Machine Learning Engineers & Data Engineers (5 people), inside the Machine Learning & AI function (15+ people) in our Data department (50+ people).
- You will contribute technically to the design and implementation of machine learning solutions and tools across the entire ML lifecycle, from model training and tuning to deployment, inference, experimentation and monitoring.
- You will collaborate with Product Managers to ensure the highest impact and quality of machine learning work for our users, as well as the best atmosphere and motivation in the team.
- You will grow your team continuously, and team up with other managers to set up the right culture and processes to enable people.
- You will work closely with data engineers and software engineers to quickly deploy end-to-end solutions with a direct impact on our users, and improve our machine learning ecosystem.
Local models hallucinated a lot more that gpt4o-mini, so I stayed with OpenAI. On top of that, I paid around 14€ for inference on ~200 examples on OVH and inference was much slower. I am planning on getting everything running on Mistral or Llama though.
I used sqlite everywhere so datasette was good for visualizing scraped and extracted data. Simon released structured generation for llm a few days after I did the project though, so I haven't tried yet.
The data is initially not at all structured, and the critics talk about a chef's CV in passing. For instance, take this example:
> At Grenat, Antoine Joannier and Neil Mahatsry are bathed in an ardent red glow, much like the pomegranate-toned walls of their space. After working together at La Brasserie Communale, where they first met, the duo is now firing on all cylinders in the heart of Marseille, where Antoine tends to guests seated around blonde wood tables, delivering dishes ignited by Neil behind the bar. From oysters to prime cuts of red meat, […]
I tried using NER models and the results were not great. Furthermore, these models do not extract relationships between entities (other models exist for that though). Haven't tried fine-tuning at all!
There is also a lot of variation in the ways of presenting a chef's prior restaurants, which makes this a good use-case for LLMs.
LLMs have without a doubt replaced NER models and libraries like SpaCy. At least for my use-cases, creating ontologies and populating knowledge graphs.
I agree the spatialization could be better. I used one of the algorithms in Gephi-lite directly. Do you have a favorite spatialization algorithm to recommend?
I made a mistake; I had checked the other link in your post ("You can explore the visualization here: [Interactive Culinary Network]") instead of the main link.
We aim to become the most beloved financial Operating System of French SMEs and Accounting Firms (and soon, European ones). We help entrepreneurs rid themselves of time-consuming tasks related to accounting and finance while providing them with access to key financial information to assist in making the best decisions for their business.
Machine Learning is core to the most-loved features in our products. The ML team is growing and we are hiring a second ML Manager.
As a Machine Learning Manager, you will lead a team of Machine Learning Engineers & Data Engineers (5 people), inside the Machine Learning & AI function (15+ people) in our Data department (50+ people). - You will contribute technically to the design and implementation of machine learning solutions and tools across the entire ML lifecycle, from model training and tuning to deployment, inference, experimentation and monitoring. - You will collaborate with Product Managers to ensure the highest impact and quality of machine learning work for our users, as well as the best atmosphere and motivation in the team. - You will grow your team continuously, and team up with other managers to set up the right culture and processes to enable people. - You will work closely with data engineers and software engineers to quickly deploy end-to-end solutions with a direct impact on our users, and improve our machine learning ecosystem.
Apply here: https://jobs.lever.co/pennylane/f5730a1c-ebf2-4965-a263-4812...
Edit: many other open positions https://jobs.lever.co/pennylane