Principal AI Solutions Engineer: Production-Ready Architect

team.blue; Gent; On-site; EUR 120,000 - 180,000; Full time

Job summary

team.blue is building the AI layer across a large digital-services ecosystem, seeking a Principal AI Solutions Engineer to own AI systems end-to-end—from model research and fine-tuning to agentic orchestration, real-time inference, and production reliability.

You will architect multi-agent platforms, design voice pipelines with latency targets, and drive ML lifecycle management, observability, and guardrails in a fast-moving team across Europe.

Qualifications

• 8+ years in ML Engineering with at least 2 years in a lead role.
• Hands-on experience with LLMs in production and prompt engineering.
• Proficiency in Python and core ML stack (PyTorch, Transformers).
• Experience with LLM inference serving in latency-sensitive environments.
• Knowledge of agentic frameworks and multi-agent tool orchestration.
• Familiarity with speech AI pipelines and real-time audio systems is a plus.
• Strong ML‑ops discipline: experiment tracking, registries, containerization, CI/CD.
• Awareness of LLM risk: hallucination, data leakage, privacy protections.

Responsibilities

• Architect and evolve multi-agent orchestration platform with plug-ins and observability.
• Design and implement voice AI pipelines with low latency targets (<300 ms).
• Build RAG pipelines with retrieval, ranking, and hybrid search over vectors and keywords.
• Define MCP server architecture and tool-use contracts across integrations.
• Fine-tune and evaluate LLMs for domain tasks like support and classification.
• Benchmark model quality with automated evals and human preferences.
• Manage model lifecycle: experiment tracking, versioning, and production promotion.
• Own AI observability stack and cost tracking; enforce guardrails for safety.
• Drive data ingestion, preprocessing, and feature pipelines for training.
• Lead CI/CD for ML, including gated evals, shadow deployments, canaries, rollbacks.
• Set architectural standards and mentor engineers in production AI.
• Collaborate with Product/Commercial teams to translate problems into ML goals.
• Engage with external researchers to identify production signals.

Skills

Python

PyTorch

Transformers (HuggingFace)

PEFT/LoRA

LLM inference serving

Langfuse observability

MLOps

Speech AI (ASR/TTS)

Multi-agent orchestration

Education

Advanced degree in ML/CS

Tools

Docker

Kubernetes

MLflow/W&B

Langfuse

vLLM / TensorRT-LLM

Job description

team.blue is building the AI layer across a large digital-services ecosystem, seeking a Principal AI Solutions Engineer to own AI systems end-to-end—from model research and fine-tuning to agentic orchestration, real-time inference, and production reliability.

You will architect multi-agent platforms, design voice pipelines with latency targets, and drive ML lifecycle management, observability, and guardrails in a fast-moving team across Europe.