Descriptif du poste

Key Responsibilities

• Architect and govern production-grade agentic systems at enterprise scale: multi-agent orchestration across complex environments, RAG pipelines, policy-based routing, memory management, and programme-level lifecycle observability

• Define RAG pipeline standards across engagements: establish chunking and embedding strategies, set quality benchmarks, and ensure metric-backed tradeoff decisions are documented and transferable

• Set multi-LLM integration standards: vendor-agnostic architecture by default, fallback routing and cost governance as standard design practice across providers including OpenAI, Anthropic, Vertex AI, and open-source models

• Own LLMOps at programme scale: eval strategy, prompt governance, observability tooling standards, safety monitoring and cost controls across multiple concurrent systems

• Lead client engineering engagements at senior level — facilitate architecture design sessions, lead proof-of-concept delivery, and drive alignment between client technology leadership and delivery teams

• Shape and publish reusable patterns, accelerators, and engineering standards that scale across the practice and reduce ramp-up time on new client engagements

• Own the measurement framework for agentic system quality: define accuracy, latency, safety, and cost metrics; present programme-level AI impact in business terms to senior client stakeholders

Basic Qualifications

• Significant years of software engineering experience in production environments

• Practical hands-on experience designing and deploying agentic AI solutions in a production environment — non-negotiable

• Demonstrated experience with agentic orchestration frameworks: LangGraph, CrewAI, AutoGen, or equivalent — at production depth, not tutorial level

• Direct experience calling LLM APIs (OpenAI, Anthropic, Vertex AI) in production code: provider abstraction, token management, latency and cost tradeoffs

• RAG pipeline ownership: embeddings, chunking strategy, vector databases, and context engineering

• LLMOps fundamentals: eval harness design, prompt versioning, and production observability

• Cloud-native engineering maturity: Kubernetes, Docker, microservices, serverless, CI/CD, and IaC (Terraform or Helm)

• Strong Python; Java or equivalent backend language acceptable; production debugging and observability experience

• Quality of experience is weighted over years, a candidate who has shipped three production agentic systems in four years is preferred over a generalist with passive AI exposure

• People lead responsibilities: experience managing, developing, and performance-managing a team of engineers; setting individual development plans and conducting career conversations