Senior AI Inference Platform Engineer

Lilasciences; Cambridge; On-site; GBP 144,480 - 204,680; Full time

Benefits offered by this job

Equity

International benefits

Job summary

Lila Sciences is seeking a Staff/Principal DevOps Engineer for AI Inference to design and optimize infrastructure for serving ML models at scale. You will bridge platform engineering, SRE, and ML infra to enable low-latency, high-throughput inference across GPU clusters and cloud accelerators.

You will collaborate with ML engineers, researchers, and software engineers to build reliable inference platforms, while maximizing compute efficiency and supporting multi-region deployments.

Qualifications

• Expertise in DevOps, SRE, or Platform Engineering operating GPU/accelerator infra at scale.
• Strong Kubernetes proficiency for ML workloads, including scheduling and device management.
• Proficient in Python for automation and tooling in ML environments.

Responsibilities

• Design and optimize GPU/accelerator infrastructure on Kubernetes for low-latency inference.
• Build and maintain model serving platforms with scalable batching and routing.

Skills

DevOps/SRE/Platform Engineering

Kubernetes for ML workloads

Python automation

Tools

Terraform

Helm

Triton Inference Server

Job description

Lila Sciences is seeking a Staff/Principal DevOps Engineer for AI Inference to design and optimize infrastructure for serving ML models at scale. You will bridge platform engineering, SRE, and ML infra to enable low-latency, high-throughput inference across GPU clusters and cloud accelerators.

You will collaborate with ML engineers, researchers, and software engineers to build reliable inference platforms, while maximizing compute efficiency and supporting multi-region deployments.