Senior AI Machine Learning Engineer for Automated Inference Pipeline Tuning

DataPro Services

Contract · Remote · Flexible hours

About the role

DataPro Services is modernizing its legacy production platform, codenamed "PulseForge", to achieve zero‑downtime deployments. As an AI Machine Learning Engineer you will embed intelligent monitoring and automated rollback mechanisms while enhancing predictive analytics pipelines.

Key responsibilities

• Design and implement a real‑time anomaly detection model using PyTorch and Kafka streams to flag performance regressions before they impact users.
• Refactor existing batch ML jobs into containerized micro‑services deployed on Kubernetes, ensuring blue‑green releases with no service interruption.
• Integrate model versioning with MLflow and automate CI/CD pipelines via GitHub Actions for seamless model promotion.
• Collaborate with the DevOps team to instrument Prometheus metrics and Grafana dashboards for end‑to‑end latency tracking.
• Conduct load testing of the new inference API (FastAPI) under simulated production traffic to validate zero‑downtime guarantees.

Must-have skills

• Strong Python expertise, including libraries such as Pandas, NumPy, and PyTorch.
• Experience building and deploying RESTful ML APIs with FastAPI or Flask.
• Proficiency in containerization (Docker) and orchestration (Kubernetes).
• Hands‑on knowledge of CI/CD tools, especially GitHub Actions or Jenkins.
• Understanding of monitoring stacks (Prometheus, Grafana) for production ML systems.

Nice to have

• Familiarity with feature store solutions like Feast.
• Background in A/B testing frameworks for model validation.