Machine-Learning Programmer

DocGPT is Ubisoft’s internal knowledge assistant platform, unveiled this year at the 2026 Games Developer Conference (GDC) and deployed across several studios and divisions. Behind the scenes, data ingestion, administration, and integration tools ensure the platform’s reliability on a daily basis. As the technical lead on these issues, you will define tooling standards and ensure that the growing demand for deployments is handled seamlessly.

You will be responsible for the technical leadership of DocGPT’s AI components: as an expert in information retrieval and LLM integration, you will set the strategic direction, guide the team, and translate sometimes ambiguous requirements into robust solutions.

What you’ll do:

• Define and oversee the technical direction of retrieval pipelines: chunking, semantic indexing, vector search, and reranking.
• Establish evaluation standards for the platform and make response quality a top priority in the development cycle.
• Define the approach to integrating large language models (LLMs) in a multi-tenant context: context management, prompt engineering, cost control, and evolution toward agent-based capabilities.
• Proactively identify the limitations of the current architecture and propose improvements before they impact users.
• Mentor junior and mid-level team members on ML best practices and experimental rigor.
• Serve as a trusted point of contact for client teams and stakeholders on AI-related topics.

What You’ll Bring to the Team:

• 5+ years of experience in applied machine learning for information retrieval systems or NLP in production.
• Proficiency in Python and ML/NLP frameworks: LangChain, LlamaIndex, HuggingFace Transformers.
• Proven experience with RAG architectures: embedding models (OpenAI, Cohere, BGE), vector databases (Qdrant, pgvector, Weaviate, Pinecone), and reranking (cross-encoders).
• Proficiency with LLM APIs (Claude, OpenAI GPT) and advanced prompt engineering techniques (few-shot, chain-of-thought, structured outputs).
• Experience with RAG evaluation frameworks: RAGAS, MRR/NDCG metrics, and building evaluation datasets.
• Familiarity with AWS and Databricks cloud environments (MLflow, Feature Store) and containerized environments.
• Demonstrated technical leadership and comfort with ambiguity; excellent communication skills.