Software Engineer: Agentic Data Pipelines for Biomedical AI

Iambic; San Diego (CA); On-site; USD 110,000 - 162,000; Full time

Benefits offered by this job

Company paid healthcare

401K matching

Uncapped vacation

Flexible spending accounts

Voluntary life insurance

Job summary

Iambic Therapeutics is seeking a software engineer to design agentic systems that turn biomedical data sources into reviewed, versioned datasets for Enchant, the multimodal transformer. You will build pipelines that can generate code to acquire, clean, format, and quality-check large-scale data and produce auditable reports.

You will work at the intersection of AI-driven automation and biomedical data engineering, focusing on reliability, security, and reproducibility in a production setting.

Qualifications

• Master’s degree in a computational STEM field, or a Bachelor’s with 2+ years of industry experience.
• Strong Python engineering skills with production-quality software experience.
• Hands-on experience with LLM APIs and agentic patterns.
• Familiarity with biomedical or chemical data formats and sources.
• Fundamentals of ETL, data validation, and working with structured/unstructured data.
• Experience with Python testing frameworks such as pytest.

Responsibilities

• Design, build, and maintain agentic systems turning data sources into reviewed, versioned datasets.
• Develop LLM-based data cleaning, normalization, and formatting pipelines.
• Implement automated quality-control workflows to detect anomalies and enforce standards.
• Collaborate with ML scientists to translate data requirements into scalable systems.
• Monitor distributed data pipelines in production and improve robustness.
• Document provenance, processing decisions, and quality metrics for reproducibility.

Skills

Python

LLM APIs

Agentic patterns

Data engineering

Pytest

Biomedical data

Cloud (AWS)

Kubernetes

Security best practices

Large-scale datasets

Education

Master’s degree or Bachelor + 2+ years

Tools

GPT/Claude APIs

Docker

Job description

Iambic Therapeutics is seeking a software engineer to design agentic systems that turn biomedical data sources into reviewed, versioned datasets for Enchant, the multimodal transformer. You will build pipelines that can generate code to acquire, clean, format, and quality-check large-scale data and produce auditable reports.

You will work at the intersection of AI-driven automation and biomedical data engineering, focusing on reliability, security, and reproducibility in a production setting.