Staff ML Infrastructure Engineer - RL & Inference Systems

Ai; Greater London; On-site; GBP 90,000 - 150,000; Full time

Job summary

Ai is building the infrastructure for cutting-edge AI and biology research in London or San Francisco. You will own the end-to-end stack for post-training and reinforcement learning, enabling researchers and AI agents to run, monitor and compare experiments with reproducible data.

The role emphasizes strong system design, scalable GPU-based workflows, and collaboration with RL, evaluation, Bio ML researchers and engineers.

Qualifications

• Experience building infrastructure for LLM inference or RL training.
• Systems fundamentals; ability to profile a slow or failing workload to its cause.
• Hands-on with GPU clusters, distributed training, model serving or high-throughput inference; scheduling, utilisation and cost.
• Docker, Kubernetes, Ray or Terraform; long-running jobs with retries, checkpointing and clear failure reporting.
• Good judgement on technical trade-offs, such as when a quick prototype is enough and when a system needs to be hardened, simplified or rebuilt.
• Clear writing and communication about system design, operational risk and engineering trade-offs.
• Fluent Python and daily use of coding agents.

Responsibilities

• Build infrastructure for post-training and reinforcement learning.
• Support training/post-training runs and inference serving; evaluate harnesses.
• Provide clear interfaces for researchers and AI agents to launch, monitor and debug runs.
• Own the stack end to end: design, implementation, deployment and maintenance.
• Set engineering standards: testing, observability and versioning; remove bottlenecks across training, rollout, evaluation and data movement.

Skills

LLM inference infra

RL training infra

GPU clusters

Profiling performance

Python

Docker

Kubernetes

System design

Cost optimization

Tools

Ray

Terraform

Docker

Kubernetes

Job description

Ai is building the infrastructure for cutting-edge AI and biology research in London or San Francisco. You will own the end-to-end stack for post-training and reinforcement learning, enabling researchers and AI agents to run, monitor and compare experiments with reproducible data.

The role emphasizes strong system design, scalable GPU-based workflows, and collaboration with RL, evaluation, Bio ML researchers and engineers.