onsite
Forward Deployed ML Engineer - Triomics
ML Engineer
Forward Deployed ML Engineer who designs, builds, and deploys AI extraction pipelines for oncology data, translating unstructured clinical documents into structured variables using Python, NLP, and cloud infrastructure.
About the role
Key Responsibilities
- Collaborate with pharmaceutical and hospital clients to understand data dictionaries and clinical document formats.
- Design, develop, and fine‑tune NLP extraction agents that convert unstructured oncology records into structured variables.
- Implement end‑to‑end pipelines, including data preprocessing, model training, validation, and performance monitoring.
- Deploy and scale extraction services on AWS using Docker and Kubernetes, ensuring reliability and low latency.
- Continuously evaluate model accuracy, perform error analysis, and iterate on solutions to meet strict regulatory and quality standards.
- Coordinate cross‑functional teams, manage timelines, and deliver production‑ready solutions under deadline pressure.
Requirements
- Strong proficiency in Python and experience with machine learning frameworks such as PyTorch or TensorFlow.
- Hands‑on expertise in Natural Language Processing techniques for information extraction.
- Experience deploying ML workloads on AWS, including containerization with Docker and orchestration with Kubernetes.
- Ability to translate complex clinical terminology into actionable data pipelines.
- Excellent communication skills for client interaction and cross‑team collaboration.
Skills
pythonmachine learningnatural language processingawsdockerkubernetes