A

Abridge

Builds AI that writes notes from doctor visits

ML Infrastructure Engineer - Machine Learning Platform

Applied Machine LearningUpdated on Nov 10
Full-timeSan Francisco, CA, USAHybrid

About the Job

Requirements

  • At least 5 years of experience building and deploying machine learning models in production environments.
  • Deep understanding of container orchestration and distributed systems architecture.
  • Expertise in Kubernetes administration, including custom resource definitions, operators, and cluster management.
  • Experience developing application programming interfaces and managing distributed systems for both batch and real-time workloads.
  • Ability to communicate effectively and interface between research and product engineering.

Responsibilities

  • Design, deploy, and maintain scalable Kubernetes clusters for AI model inference and training.
  • Develop, optimize, and maintain machine learning model-serving infrastructure for high performance and low latency.
  • Collaborate with machine learning and product teams to scale backend infrastructure for AI-driven products, focusing on model deployment, throughput optimization, and compute efficiency.
  • Optimize compute-heavy workflows and enhance GPU utilization for machine learning workloads.
  • Build a robust model application programming interface orchestration system.
  • Collaborate with leadership to define and implement strategies for scaling infrastructure as the company grows, ensuring long-term efficiency and performance.

Desired Qualifications

  • Expertise with model-serving frameworks such as NVIDIA Triton Server, vLLM, and TensorRT-LLM.
  • Expertise with machine learning toolchains such as PyTorch, TensorFlow, or distributed training and inference libraries.
  • Familiarity with GPU cluster management and CUDA optimization.
  • Knowledge of infrastructure as code tools such as Terraform and Ansible, and GitOps practices.
  • Experience with container registries, image optimization, and multi-stage builds for machine learning workloads.
  • Experience orchestrating across automatic speech recognition or large language models to build generative AI applications.

About the Company

Abridge

Builds AI that writes notes from doctor visits

Abridge builds AI software that listens to conversations between clinicians and patients and drafts the clinical notes doctors would otherwise type, mainly for large health systems. In 2024, Kaiser Permanente rolled it out across its hospitals and medical offices in what was then the largest generative AI deployment in health care. With the patient's consent, clinicians record the visit, and a structured note is ready in their electronic health record when it ends, with each part traceable to the transcript and audio. It also captures orders, billing codes, and patient summaries, and health systems pay for it through enterprise subscriptions. Abridge was founded in Pittsburgh in 2018 and is based in San Francisco.

Company size
201-500
Company stage
Series E
Total funding
$757.5M
Headquarters
San Francisco, CA
Founded
2018

Recently Posted Jobs

Explore more opportunities at Abridge

See more jobs