ML Ops Engineer: Medical AI Infra Lead

Voio; Berkeley (CA); On-site; USD 150,000 - 210,000; Full time

Job summary

Voio is redefining how radiologists work with a unified medical AI platform. We’re building production-ready systems from research to real-world use, backed by UC Berkeley/UCSF origins. The role focuses on scalable ML infrastructure for fast, secure clinical workflows.

Join a team that values clarity, ownership, and judgment as you deploy GPU inference, optimize runtimes, and deliver observable, high-performance pipelines for real-time medical AI.

Qualifications

• 4+ years of experience in ML Ops, infrastructure, or distributed systems.
• Proficiency with Triton Inference Server, TensorRT, and PyTorch optimization.
• Strong background in GPU-based debugging, profiling, and system tuning.
• Experience with Docker, Kubernetes, and cloud deployment (AWS or GCP).
• Ability to operate independently and make clear, impact-driven tradeoffs.

Responsibilities

• Deploy and maintain GPU inference systems using Triton Inference Server and TensorRT.
• Build and optimize CI/CD pipelines for model training, testing, validation, and rollout.
• Tune PyTorch deployments for latency, memory, and throughput efficiency.
• Design observability and monitoring tools to track inference performance, drift, and uptime.
• Benchmark and profile models in production, driving continuous improvements across the stack.
• Partner with research and product teams to operationalize models for real-time clinical workflows.

Skills

ML Ops

Distributed systems

Independent work

Cloud deployment

Tools

Docker

Kubernetes

Triton Inference Server

TensorRT

PyTorch optimization

Job description

Voio is redefining how radiologists work with a unified medical AI platform. We’re building production-ready systems from research to real-world use, backed by UC Berkeley/UCSF origins. The role focuses on scalable ML infrastructure for fast, secure clinical workflows.

Join a team that values clarity, ownership, and judgment as you deploy GPU inference, optimize runtimes, and deliver observable, high-performance pipelines for real-time medical AI.