You build the runway. Training pipelines, model registries, feature stores, evaluation, deployment, observability and cost governance - you turn ML from artisanal to industrial across every AutoThink product.
What you'll build
- A shared ML/LLM platform used by every AutoThink product team.
- CI/CD for models, prompts and evaluations.
- Cost and latency observability across every model call.
- Secure, multi-tenant inference infrastructure.
Requirements
- 5+ years platform / infra / DevOps, ideally with an ML flavour.
- Strong Kubernetes, Terraform, CI/CD.
- Comfortable with GPU workloads and inference optimisation.
- Security and compliance mindset (SOC2, ISO 27001, UK GDPR).
- Right to work in the UK.
#J-18808-Ljbffr
This role, MLOps Engineer at AutoThink Group, could be your next move.
We aim to respond to suitable candidates as soon as possible.
Full responsibilities and requirements are described in the listing above.