AI Native Engineer
Remote • Paris
Posted 27d ago
About the job
You will design, build, and deploy production-grade agentic AI systems across the full enterprise technology stack. This role involves working directly with client engineering teams, leading technical design sessions, and building reusable patterns and accelerators that scale beyond individual engagements. The focus is on shipping production agentic architectures, owning evaluation harnesses, and understanding the operational aspects of AI systems in real-world enterprise environments.
Responsibilities
- Design and build production-grade agentic systems end-to-end, including multi-agent orchestration, RAG pipelines, policy-based routing, tool invocation, memory management, and lifecycle observability.
- Build and own RAG pipelines, focusing on embeddings, chunking strategy, vector search, and context window engineering.
- Integrate and abstract across multiple LLM providers (e.g., OpenAI, Anthropic, Vertex AI, open-source models) with fallback routing, token, cost, and latency management.
- Implement LLMOps in production, including eval harnesses with real quality metrics, prompt versioning, and observability tooling.
- Embed directly with client engineering teams to design, prototype, and deploy agentic solutions.
- Build reusable patterns, accelerators, and playbooks to enable faster client engagements.
- Define and use metrics to measure agent accuracy, latency, safety, and cost-effectiveness, and present findings to stakeholders.
Requirements
- 2 to 5 years of software engineering experience in production environments.
- Minimum 1 year of hands-on experience designing and deploying agentic AI solutions in a production environment.
- Demonstrated experience with agentic orchestration frameworks like LangGraph, CrewAI, or AutoGen at a production depth.
- Direct experience calling LLM APIs (OpenAI, Anthropic, Vertex AI) in production code, including provider abstraction and token management.
- Experience with RAG pipeline ownership, including embeddings, chunking strategy, vector databases, and context engineering.
- Understanding of LLMOps fundamentals: eval harness design, prompt versioning, and production observability.
- Cloud-native engineering maturity, including Kubernetes, Docker, microservices, serverless, CI/CD, and IaC (Terraform or Helm).
- Strong Python skills; Java or equivalent backend language is acceptable.
- Production debugging and observability experience.