Senior AI Inference DevOps Engineer

Lila Sciences; Cambridge (MA); On-site; USD 192,000 - 272,000; Full time

Benefits offered by this job

Equity in company equity

Medical, dental, vision coverage

Generous PTO and holidays

Job summary

Lila Sciences is seeking a Staff/Principal DevOps Engineer for AI Inference in Cambridge, MA. You will design and optimize GPU-accelerated infrastructure for scalable ML model serving, spanning Kubernetes clusters, Terraform/Helm deployments, and multi-region pipelines.

You will collaborate with ML researchers, software engineers, and data scientists to build reliable inference platforms with maximum GPU utilization and minimal latency.

Qualifications

• Expertise in DevOps/SRE/Platform Engineering for GPU/accelerator infra at scale.
• Deep experience with Kubernetes for ML workloads and GPU scheduling.

Responsibilities

• Design and optimize GPU/accelerator infrastructure on Kubernetes and cloud platforms.
• Build model serving platforms with low latency and high throughput.
• Implement CI/CD pipelines and IaC for GPU-based EKS clusters.

Skills

DevOps

SRE

Platform Engineering

Kubernetes

Python

Tools

Terraform

Helm

AWS

Triton Inference Server

Job description

Lila Sciences is seeking a Staff/Principal DevOps Engineer for AI Inference in Cambridge, MA. You will design and optimize GPU-accelerated infrastructure for scalable ML model serving, spanning Kubernetes clusters, Terraform/Helm deployments, and multi-region pipelines.

You will collaborate with ML researchers, software engineers, and data scientists to build reliable inference platforms with maximum GPU utilization and minimal latency.