Forward Deployed ML Engineer
TriomicsOncology AI company
New York, United StatesMid
Battery Ventures
Lightspeed
Y Combinator
Nexus Venture Partners
Oncology Ventures
Precision Health Informatics
Data & AI
About the role
TL;DR
Build and deploy AI agent pipelines for extracting structured oncology variables from patient documents.
- •Build and deploy AI agent pipelines that extract structured oncology variables from unstructured patient documents for pharmaceutical companies and cancer hospitals.
- •Key Responsibilities Design and build agentic extraction pipelines that process 500+ page patient charts and output structured JSON per customer data dictionaries.
- •Own accuracy end-to-end: define evaluation datasets, run precision/recall analysis per variable, identify failure modes, and improve through agent architecture changes, prompt engineering, fine-tuning, or rule-based post-processing.
- •Go deep into the clinical source data
- •read the actual patient charts, understand how oncologists document, learn why certain data points are ambiguous and use that understanding to improve extraction.
- •Work with the clinical annotation team to build gold-standard datasets and resolve edge cases.
- •Coordinate with customer data science and clinical teams to clarify dictionary definitions, review output quality, and close accuracy gaps.
- •Requirements 2+ years building ML/AI systems in production Built and deployed AI agents or multi-step LLM pipelines Strong Python Practical LLM experience: prompt engineering, fine-tuning, RAG, evaluation design Built evaluation frameworks for LLM based document extraction tasks Willingness to become a domain expert in oncology data Comfortable owning customer-facing communication alongside technical delivery Can operate in high-intensity delivery sprints and manage your own time across multiple workstreams
Required skills
PythonTensorFlowPyTorchscikit-learnHugging FaceLLMsMLflowKubeflowONNXJAXPandasNumPyApache KafkaAWSDocker
Domain expertise
healthcare
Tech stack
PythonMLflowKubeflowONNXJAXPandasNumPyTensorFlowPyTorchscikit-learnHugging FaceLLMsApache KafkaAWSDockerKubernetesCI/CDGitLinux