Sr ML Engineer

About the role

A senior role leading the move of machine learning systems into production and keeping them reliable, scalable and cost effective in demanding environments.

What you will do

• Own the full production lifecycle of ML systems, from training and packaging to deployment, monitoring and controlled releases
• Design and refine training and retraining pipelines covering data intake, labeling checks, feature creation and experiment tracking
• Build and tune high performance inference services and deployment patterns
• Improve inference speed and cost through runtime optimization, quantization, batching and hardware tuning
• Work with DevOps and SRE colleagues on scaling, reliability, incident readiness and observability
• Manage model versioning, CI/CD and release workflows so results are reproducible and safe to ship

What they look for

• Advanced degree or comparable experience in computer science, engineering or data science with solid math, statistics and ML grounding
• Six or more years across ML engineering and production ML or MLOps, with a record of shipping impactful systems
• Proven ability to deploy models: serving patterns, packaging, inference optimization, observability and safe rollouts
• Experience tuning model efficiency: latency, throughput, batching, quantization, ONNX or TensorRT, GPU and CPU use
• Strong Python skills and hands on work with PyTorch, scikit-learn and runtime stacks such as ONNX and TensorRT
• Familiarity with CI/CD for ML, Docker, monitoring, drift detection, alerting, SLOs and incident response