Tech Lead, Gen AI

You provide the technical leadership on our generative AI projects: architecture, RAG pipelines, model selection and production rollout on GCP. You are the team's technical reference and the point of contact for client-side sponsors. The role calls for more than 8 years of software engineering experience, including more than 3 years dedicated to AI/ML or GenAI platforms.

• Design event-driven micro-services architectures on GCP
• Architect end-to-end RAG pipelines: ingestion, chunking, retrieval, generation
• Lead the choice of LLMs (Mistral and Anthropic (Claude) against open-source options) with rigorous cost/benefit logic
• Optimize GenAI costs: token budgeting, embedding caches, model tiering
• Define network and access security patterns (IAP, VPC-SC, Secret Manager)
• Ensure Cloud Run scalability: cold starts, load testing
• Write ADRs and enforce the Definition of Done
• Mentor engineers through code reviews, pair programming and design walkthroughs

• More than 8 years in software engineering, including more than 3 years in AI/ML or GenAI
• Proven experience leading a technical team and managing technical debt
• Production command of GCP: Vertex AI (Vector Search), Cloud Run, Pub/Sub, GCS, VPC-SC, IAP, Secret Manager
• RAG in production: ingestion, advanced chunking, retrieval, generation
• LLM evaluation and selection, fine-grained cost management
• A solid command of Python
• Quality communication with teams and sponsors

Valued extras: Google Cloud certification, LangChain/LlamaIndex, Weaviate/Pinecone, TypeScript/Node.js, LLM observability tools.