Senior Ai/Ml Engineer
Posted Updated
Description
Team.Blue in Toscana, Italy seeks a Principal AI Solutions Engineer to own end-to-end AI systems, set technical direction, and ship production AI across a fast-moving team. You will lead across model research, fine-tuning, agent-based orchestration, and real-time inference for hosting, domains, email, and SaaS for millions of SMBs.
Responsibilities include evolving multi-agent orchestration platforms, building low-latency voice AI pipelines, and developing RAG pipelines with rigorous quality
Architect and evolve multi-agent orchestration platform (Hermes / Multica). Design and implement voice AI pipelines with low latency. Build and maintain RAG pipelines with retrieval quality measurement and hybrid search. Define MCP server architecture and tool-use contracts across integrations. Fine-tune and evaluate LLMs for domain tasks and production lifecycle. Own AI observability stack (tracing, instrumentation, cost tracking). Drive ML CI/CD, shadow deployments, canary releases; mentor engineers. 8+ years in ML Engineering, with leadership experience. Hands-on production LLMs experience: fine-tuning, RLHF/DPO, prompt engineering. Proficient in Python and core ML stack (PyTorch, Transformers, PEFT/LoRA). Experience with latency-sensitive LLM inference (vLLM, TensorRT-LLM, or TGI). Knowledge of multi-agent orchestration, tool-use, and observability. Awareness of LLM risk management (privacy, data leakage, hallucination).Skills
Sign in to read and join the discussion.