Job Description
Crucial hire!
- This fast-moving AI group is building production-grade LLM systems for real-world enterprise use cases. They’re looking for an MLOps Engineer to own the infrastructure, orchestration, and CI/CD that power their LLM workloads at scale.
- You’ll be the go-to person making sure cutting-edge models run fast, stable, and cost-efficiently in production.
TL;DR
📍 Location: Amsterdam (relocation & visa sponsorship available)
💼 Env: AI / LLM / infra-first engineering
⚡ Mission: Run LLMs at scale - build APIs, optimise inference, empower ML teams
🔧 Tech: Python, FastAPI, vLLM, TGI, K8s, Terraform, MLflow, W&B, GCP/AWS, Ray
🗣 Language: English-first environment
- Salary? Up to 140k
Role
- You’ll design and maintain GPU-powered ML pipelines from data to inference, build high-performance APIs for LLM services, and own CI/CD, observability, and versioning for ML systems.
- You’ll be working closely with ML engineers and researchers to turn prototypes into reliable, production-grade LLM products.
Who?
✔ 3–5+ years in MLOps / DevOps for ML systems
✔ Strong Kubernetes + Python API skills
✔ Hands-on with vLLM, TGI, KServe, or similar inference frameworks
✔ Bonus: Ray, Argo Workflows, GPU optimisation, or safe rollout strategies
✔ Calm under pressure, loves squeezing performance out of infra
Why Join?
🚀 Shape how LLM workloads are deployed and scaled for real customers
🤝 High-trust, engineering-driven culture with plenty of room to own decisions
🌍 Relocation & visa sponsorship on offer
Similar Jobs
Explore other opportunities that match your interests