9 months ago
Paris, FranceSenior
Responsibilities
- Design and develop agentic AI architectures capable of autonomous reasoning and complex task execution.
- Orchestrate multi-agent systems for cross-functional business use cases.
- Select and fine-tune open-source or proprietary models according to performance and cost requirements.
- Build robust RAG pipelines, vector indexing systems, semantic search capabilities, APIs, and integrations with existing application ecosystems.
- Deploy Generative AI solutions in secure and scalable production environments.
- Implement LLM monitoring, guardrails, response-quality tracking, latency and cost monitoring, CI/CD chains, and continuous model-evaluation pipelines.
- Track developments in the GenAI ecosystem, advise business stakeholders on use-case feasibility, and contribute to internal technical best practices.
Requirements
- Bac+5 engineering or university education specializing in AI or computer science.
- Expert proficiency in Python.
- Proven experience with GenAI frameworks such as LangChain, LlamaIndex, Haystack, and AutoGen.
- Knowledge of vector databases including Pinecone, Weaviate, Qdrant, and Milvus.
- Familiarity with Docker, Kubernetes, and model-monitoring tools such as LangSmith, MLflow, and Arize.
- Prior production experience with LLM-based solutions beyond proof-of-concept work.
- Ability to explain complex concepts to non-technical stakeholders and work rigorously in demanding environments.
Benefits
- Ambitious and varied consulting assignments selected for their business value.
- Close support from recognized experts.
- Access to an engineering community with workshops, conferences, and regular knowledge exchange.
- A culture focused on technical excellence, knowledge sharing, and continuous development.
Tech Stack
Categories
