Platform Engineer - Self Hosting LLMs
PhysicsX · London
Frontier labonsite
At a glance
Highlights
- Build the LLM access layer powering agents across the PhysicsX platform.
- Make agentic capabilities work out of the box with no customer key needed.
- Enable reliable serving in air-gapped, constrained customer environments.
Ideal candidate
Production-minded platform engineer who loves owning reliable inference systems end-to-end and balancing cost, quality and latency. You thrive wiring complex systems into real platforms and shaping technical direction.
Requirements
- Operated inference engines such as vLLM or SGLang or serving platforms such as KServe under production constraints
- Built or operated model routing across more than one provider balancing cost, quality, latency and policy
- Strong containers, Kubernetes, networking, storage and distributed-systems fundamentals
- GPU observability and performance analysis across engine, system and accelerator metrics
- Experience with model formats, quantisation, tokenisation and OpenAI-compatible serving APIs
- Traffic management, streaming, overload protection, health checking and failure recovery
- Integration with identity, authorisation, secrets and workload-isolation systems
- Clear technical writing, design review, incident response and cross-team communication
Lab profile
About PhysicsX
Physics AI company building simulation software to accelerate industrial hardware innovation.
What they build
- Simulation software stack for industrial engineering
Known for
- Physics AI
- Aerospace & defence
- CFD and manufacturing engineering
Posted · Last seen