Company description
Ubisoft is a global leader in video games, with teams spread across the four corners of the world who create original and memorable gaming experiences, from Assassin's Creed to Rainbow Six, including Just Dance and many more. We believe that diversity of perspectives drives progress for both players and teams.
If you are passionate about innovation and want to push the limits of entertainment, join our adventure and help us create the unknown!
Job description
DocGPT is Ubisoft's internal knowledge assistant platform, presented this year at the Games Developer Conference (GDC) 2026 and deployed on a large scale across studios and divisions. Based on a RAG architecture, it allows thousands of employees to find relevant information directly from their everyday tools.
You will take on the technical leadership of the AI components of DocGPT: as the reference point for information retrieval and LLM integration challenges, you will set the direction, support the team and turn sometimes ambiguous requirements into robust solutions.
What you will do:
- Define and drive the technical direction of retrieval pipelines: chunking, semantic indexing, vector search, reranking.
- Establish the platform's evaluation standards and make response quality a leading metric throughout the development cycle.
- Define the LLM integration approach in a multi-tenant context: context management, prompt engineering, cost control, evolution toward agentic capabilities.
- Proactively identify the limits of the current architecture and propose evolutions before they impact users.
- Mentor junior and intermediate members on ML best practices and experimental rigor.
- Be the trusted point of contact for client teams and stakeholders on AI topics.
Qualifications
What you will bring to the team
- 5+ years of experience in applied ML on production information retrieval or NLP systems.
- 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), reranking (cross-encoders).
- Mastery of 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, building evaluation datasets.
- Knowledge of AWS and Databricks cloud environments (MLflow, Feature Store) and containerized environments.
- Demonstrated technical leadership and comfort with ambiguity; excellent communication skills.
Additional information
About us
Ubisoft's teams number 20,000 people spread across more than 30 countries around the world and are united by a common mission: enriching the lives of players through original and memorable gaming experiences. Their energy and talent have brought to life many acclaimed franchises such as Assassin's Creed, Far Cry, Watch Dogs, Just Dance, Rainbow Six and many more to come.
Ubisoft is an equal opportunity employer and believes that diversity of backgrounds and perspectives is essential to creating worlds that allow everyone to thrive and express themselves.
Working at Ubi MTL means enjoying a work environment that sparks creativity and fosters connection. We offer a collaborative space focused on career growth, learning opportunities and well-being (our substantial benefits are proof of this!).
If you are excited about taking on thrilling challenges, leveraging the latest technologies and taking part in the future of entertainment, join us to create the unknown.
At Ubisoft, you are welcome as you are. We welcome diversity in all its forms. We are committed to fostering an inclusive work environment that respects all differences.