Job Description :

We are looking for an NLP ML Engineer intern to join our team and contribute to our expansion.

Under the supervision of our ML Engineer, you will work in an agile, AI-driven environment where your contributions will have a direct and crucial impact on our business.

Your role will be essential in developing AI algorithms that will serve as a pillar for our Generative Customer Service solution.

Responsibilities :

• R&D : Conduct in-depth research on state-of-the-art topics such as NLP, retrievers, LLMs, and Prompt Engineering with a significant impact on our startup.

• Modeling : Develop, train, and monitor retrievers and LLMs models tailored to our business data.

• Advanced RAG : Implement new RAG (Retrieval Augmented Generation) techniques and orchestration of LLM agents.

• NLP use cases : Implement ML algorithms to NLP tasks such as text classification, clustering, NER (Named Entity Recognition), etc.

• Optimization ANN : Improve ANN (Approximate Nearest Neighbors) similarity search and index configuration on vector databases to ensure minimal query time and maximum recall.

• Collaboration : Work closely with other developers for seamless model deployment

What We Offer :

• Real Responsibilities : We trust you 100%: it’s up to you to succeed!

• Dynamic Environment : An agile framework that allows quick decision-making to have an impact every day.

• Unique Opportunity : In a fast-growing startup addressing a fast-growing market, you will grow every day and have the pleasure of participating in a real adventure.

• Experience : Graduate from top engineering schools (X, Centrale, Ponts, Mines, Telecom, etc.)

• Technical Skills : Expertise in Python, NLP, machine learning algorithms, libraries like PyTorch, transformers, etc. Knowledge of frameworks such as LangChain, vLLM, etc. is a plus.

• Soft Skills : Excellent communication, synthesis abilities, problem-solving skills, and teamwork capabilities.

• Discovery and technical interview with Yassine, ML Engineer

• Interview with Yoann, CTO