onsite
Machine Learning Infrastructure Engineer - Model Inference - abridge
ML Engineer
Lead the design and deployment of scalable ML inference pipelines on AWS, leveraging Docker, Kubernetes, and CI/CD to deliver real‑time, auditable medical conversation models.
About the role
Key Responsibilities
- Architect and maintain end‑to‑end ML inference pipelines for real‑time clinical note generation.
- Containerize models with Docker and orchestrate deployments on Kubernetes clusters.
- Implement CI/CD workflows to automate model testing, validation, and rollout.
- Collaborate with data scientists to optimize inference latency and throughput.
- Ensure compliance with healthcare data security and audit requirements.
Requirements
- Strong experience with Python and ML frameworks (PyTorch, TensorFlow).
- Proficiency in AWS services (EKS, ECS, S3, Lambda, SageMaker).
- Hands‑on knowledge of Docker, Kubernetes, and Helm.
- Familiarity with CI/CD tools (GitHub Actions, Jenkins, ArgoCD).
- Excellent problem‑solving skills and a passion for building reliable, scalable systems.
Skills
pythonmachine learningawsdockerkubernetescicd