Iambic Therapeutics
Software Engineer — Agentic data pipelines
About this role
Build LLM-powered agentic systems that automatically acquire, clean, and curate biomedical datasets for training Enchant, a multimodal transformer model. You'll develop AI agents that generate trustworthy pipeline code, implement quality controls, and maintain production data workflows at scale.
What you'll do
- Design agentic systems that convert biomedical data sources into versioned, reviewed datasets with reproducible pipeline code and test suites
- Develop LLM-based pipelines for data cleaning, normalization, and formatting across diverse modalities (molecular, genomic, clinical, literature)
- Implement automated quality-control workflows to detect anomalies and enforce data standards
- Evaluate and improve agent architectures, prompting strategies, and validation loops to increase reliability and throughput
- Monitor and maintain distributed data pipelines in production, diagnosing failures and improving robustness
- Operate agents safely with sandboxed execution, least-privilege credentials, and comprehensive audit logging
What they're looking for
- Python production-quality software development
- LLM APIs (Claude, GPT) and agentic patterns (tool use, orchestration, reasoning)
- Biomedical data formats (PDB, UniProt, ChEMBL, SDF/MOL, FASTA)
- Data engineering fundamentals (ETL, validation, structured/unstructured data at scale)
- Python testing frameworks (pytest, parametrization, fixtures)
- Agent orchestration frameworks and LLM-generated code evaluation
- Cloud infrastructure and workflow orchestration (AWS, Docker, Kubernetes)
- Agent security practices (sandboxing, credential scoping, prompt injection mitigation)
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Iambic Therapeutics
Iambic Therapeutics builds Enchant, a multimodal transformer model designed to accelerate drug discovery through AI-powered clinical prediction and therapeutic decision-making. The company is hiring Machine Learning Scientists to develop and deploy the model, including roles focused on fine-tuning for clinical tasks, building biomedical data pipelines, and advancing model architectures and training at scale.
View all jobs at Iambic TherapeuticsLikely interview questions
- Walk us through your experience building production software with LLMs—what agent patterns have you used, and what challenges did you encounter scaling them?
- Describe a time you worked with biomedical or scientific data. How did you approach data quality and validation?