Machine Learning Infrastructure Engineer

Harnham is an early-age cutting-edge organization seeking a Machine Learning Engineer to drive infrastructure scalability across state-of-the-art GenAI products. The role involves building and scaling ML infrastructure, optimizing models for performance, and architecting deployment strategies to support growth and complexity.

Responsibilities:

• Build and scale ML infrastructure capable of serving high-volume, low-latency model inference
• Optimize models and pipelines for performance, cost, and reliability in production environments
• Productionize research and experimental models into scalable, maintainable ML systems
• Architect infrastructure and deployment strategies that support continuous growth and evolving model complexity
• Drive infrastructure development to handle a variety of models

Requirements:

• Experience in ML platform infrastructure and deployment, including scaling training / inference, concurrency, queuing, back pressure, orchestration
• Design and operate high-performance model serving systems with proven ownership of system stability, not just in deployment
• Engineer solutions that efficiently manage parallel inference workloads at scale
• Tune end-to-end serving pipelines to maximize responsiveness and overall system capacity
• Python
• AWS native stack
• Docker, containers, SageMaker, Kubernetes