Agentic Data Pipelines Engineer — Biomedical AI

Matcha; Northern (KY); Hybrid; USD 120,000 - 180,000; Full time

Benefits offered by this job

Competitive pay

Healthcare

401K matching

Unlimited vacation

Onsite gym

Job summary

Iambic Therapeutics is seeking a software engineer to join our team and build data acquisition and curation pipelines for Enchant, our multimodal transformer model. You will design agentic systems that generate, clean, and audit datasets powering large-scale training, with code that runs pipelines and test suites.

The role blends strong software engineering with biomedical data understanding, using LLMs to solve practical data problems at scale in our San Diego facility.

Qualifications

• Master’s degree in a computational STEM field or a Bachelor’s with 2+ years of industry experience.
• Strong Python engineering skills and production-quality software.
• Hands-on experience with LLM APIs (Claude, GPT) and agentic patterns.
• Familiarity with biomedical/chemical data sources and formats.

Responsibilities

• Design, build, and maintain agentic systems that turn data sources into reviewed, versioned datasets with code and tests.
• Implement automated quality-control workflows for data standards and anomaly detection.
• Evaluate and iterate agent architectures, prompting strategies, and evaluation harnesses.
• Collaborate with ML scientists to translate data requirements into scalable pipelines.
• Monitor distributed data pipelines in production and diagnose failures.
• Document data provenance, processing decisions, and quality metrics.

Skills

Python

LLM APIs

Data engineering

Testing with pytest

Biomedical data

Education

Master’s degree in STEM

Bachelor’s degree + 2+ years experience

Tools

AWS

Docker

Kubernetes

Git

Job description

Iambic Therapeutics is seeking a software engineer to join our team and build data acquisition and curation pipelines for Enchant, our multimodal transformer model. You will design agentic systems that generate, clean, and audit datasets powering large-scale training, with code that runs pipelines and test suites.

The role blends strong software engineering with biomedical data understanding, using LLMs to solve practical data problems at scale in our San Diego facility.