Senior AI Machine Learning Engineer – Eval Harness Design

Pinecrest Systems

Contract · Remote · Flexible hours

About the role

Pinecrest Systems is revamping the performance and reliability of its flagship customer‑facing services. As an AI Machine Learning Engineer you will lead the redesign of the predictive analytics layer for the new PulseGuard module, ensuring low‑latency, high‑throughput inference across global traffic spikes.

Key responsibilities

• Architect and implement a scalable TensorFlow Serving pipeline on Kubernetes for real‑time scoring.
• Refactor legacy PyTorch models into ONNX format and benchmark latency improvements.
• Develop automated CI/CD workflows using GitHub Actions and MLflow for model versioning.
• Instrument monitoring dashboards in Grafana to track inference latency, error rates, and resource utilization.
• Collaborate with backend engineers to integrate model endpoints into existing REST APIs, achieving sub‑100 ms response times.
• Deliver a performance report after each sprint, highlighting reliability gains and regression fixes.

Must-have skills

• Deep expertise in Python for data pipelines and model training.
• Proficiency with TensorFlow, PyTorch, and model conversion tools.
• Strong experience deploying ML models on Docker/Kubernetes environments.
• Solid understanding of REST API design and integration.
• Ability to profile and optimise GPU/CPU workloads for latency.

Nice to have

• Familiarity with MLOps platforms such as Kubeflow or SageMaker.
• Experience with A/B testing frameworks for model validation.