Description

•    Translate data science prototypes into production-grade ML services and pipelines. 
•    Build training and inference code with reproducibility, versioning, and automated testing. 
•    Implement scalable model serving (online/offline), batching, and latency/throughput optimization. 
•    Integrate model lifecycle tooling (tracking, registry, deployment automation, monitoring). 
•    Collaborate with Data Engineering on feature pipelines and data contracts. 
•    Own production health: drift detection, performance regression, rollback strategies, and incident response. 
•    5+ years software engineering with 2+ years shipping ML models to production. 
•    Strong Python skills and experience with ML frameworks (TensorFlow/PyTorch). 
•    Experience with containers and orchestration (Docker/Kubernetes) and API development. 
•    Understanding of ML system design (data leakage, training-serving skew, drift)

Key Skills

Education

Bachelor's degree