AI Practice
Postuler à ce poste AI/ML Engineer
Build production AI features for client products, from retrieval-augmented pipelines to narrow, embedded automations, with a strong focus on evaluation and reliability over demos.
Vos missions
- Design and ship LLM-powered features using the Claude and OpenAI APIs
- Build retrieval-augmented generation (RAG) pipelines with vector databases
- Define evaluation harnesses to measure model output quality before and after changes
- Implement guardrails, structured outputs, and tool-calling patterns for production reliability
- Work with client stakeholders to scope AI features that solve a specific workflow problem
Profil recherché
- 2+ years building production systems that integrate LLM APIs (not just prototypes)
- Strong Python or TypeScript skills
- Experience with vector databases (Pinecone, Weaviate, pgvector) and embedding models
- Understanding of prompt engineering, context management, and token/cost tradeoffs
- Ability to reason about failure modes and design for graceful degradation
Atouts supplémentaires
- Experience fine-tuning or evaluating open-source models
- Familiarity with agentic frameworks and tool-use patterns
- Background in NLP or applied machine learning
Intéressé par ce poste ? Envoyez-nous votre CV et une courte note expliquant pourquoi vous êtes fait pour ce rôle.
Postuler à ce poste