← All roles

Forward Deployed ML Engineer

Triomics· Engineering
Apply on company site
Hybrid (New York, NY)$170k - $190kFull-timePosted 6mo ago

About the role

Role focused on building and deploying AI agent pipelines to extract structured oncology data from unstructured clinical documents, owning end-to-end delivery for customer dictionaries and ensuring production-grade accuracy in oncology EHR workflows.

Responsibilities

  • Design and build agentic extraction pipelines that process 500+ page patient charts (clinical notes, pathology reports, imaging reports, genomic panels) 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
  • Coordinate with internal engineering and infrastructure teams to deploy, scale, and monitor pipelines in production
  • Deliver on customer timelines - intense sprint periods around customer deliveries followed by iteration and improvement cycles

Qualifications

  • 2+ years building ML/AI systems in production
  • Built and deployed AI agents or multi-step LLM pipelines (not just single-call wrappers)
  • Strong Python - pipeline code, data processing, infrastructure glue
  • Practical LLM experience: prompt engineering, fine-tuning, RAG, evaluation design
  • Built evaluation frameworks for LLM based document extraction tasks (precision, recall, per-class analysis, error taxonomy)
  • Willingness to become a domain expert in oncology data
  • Comfortable owning customer-facing communication alongside technical delivery
  • Able to operate in high-intensity delivery sprints and manage time across multiple workstreams

Skills

Required:Agent architecture and orchestrationPythonLLM prompts and fine-tuning
Last updated Oct 7, 2026. Interested? Apply on the company site.
Triomics logo

About Triomics

Generative AI for Oncology EHRs

Triomics is helping cancer care providers by reducing the burden associated with manually reviewing patient charts. Utilizing our OncoLLM™—a family of oncology-focused language models—we are able to accelerate clinical trial enrollment, power quality improvement projects, and address many other key strategic priorities.

healthcarehealthcare-it
Company profileWebsite

More open roles at Triomics