ML Infrastructure Engineer — Scalable AI & GPU, Equity

FDE Times; Abridge; Remote; GBP 90,000 - 130,000; Full time

Benefits offered by this job

Generous Time Off

Comprehensive Health Plans

401(k) Matching

Parental Leave

Flexible Spending Accounts

Sabbatical Leave

Job summary

Abridge is seeking an ML Infrastructure Engineer to design, deploy and optimize the core inference infrastructure powering our machine learning models. You will collaborate with Infrastructure and Research teams to build, deploy and orchestrate AI workloads at scale.

The role emphasizes scalable Kubernetes-based deployment, high performance model serving, and GPU utilization optimization, with strong emphasis on collaboration across research and product teams.

Qualifications

• 5+ years of experience building and deploying ML models in production.
• Deep understanding of container orchestration and distributed systems architecture.
• Expertise in Kubernetes administration with CRDs, operators and cluster management.
• Experience developing APIs and managing distributed systems for batch and real-time workloads.
• Excellent communication skills bridging research and product engineering.

Responsibilities

• Design, deploy and maintain scalable Kubernetes clusters for AI model inference and training.
• Develop, optimize, and maintain ML model serving infrastructure with low latency.
• Collaborate with ML and product teams to scale backend infra for AI products, focusing on deployment, throughput and compute efficiency.
• Optimize compute-heavy workflows and improve GPU utilization for ML workloads.
• Build a robust model API orchestration system.
• Define and implement scaling strategies to support company growth for long-term efficiency.

Skills

Kubernetes administration

Distributed systems

API development

GPU/CUDA optimization

Terraform/Ansible

GitOps practices

Tools

NVIDIA Triton Server

PyTorch / TensorFlow

Docker

CI/CD tooling

Job description

Abridge is seeking an ML Infrastructure Engineer to design, deploy and optimize the core inference infrastructure powering our machine learning models. You will collaborate with Infrastructure and Research teams to build, deploy and orchestrate AI workloads at scale.

The role emphasizes scalable Kubernetes-based deployment, high performance model serving, and GPU utilization optimization, with strong emphasis on collaboration across research and product teams.