Software Engineer — Agentic data pipelines
Iambic Therapeutics, Inc3 hours ago
Remote, United StatesMid Level
Base Salary
$110k - $162k/yr
Responsibilities
- Build and maintain agentic systems that acquire, clean, normalize, format, quality-control, and version biomedical datasets from heterogeneous sources.
- Develop LLM-based pipelines whose generated code and test suites enable reproducible dataset creation.
- Implement automated quality-control workflows to detect anomalies, flag inconsistencies, and enforce data standards.
- Evaluate agent architectures, prompting strategies, tool definitions, validation loops, and evaluation harnesses to improve reliability and throughput.
- Collaborate with ML scientists to translate Enchant data requirements into scalable acquisition and processing systems.
- Monitor and maintain distributed production data pipelines, diagnose failures, and improve robustness.
- Document data provenance, processing decisions, and quality metrics for reproducibility and auditing.
- Operate agents securely using sandboxed execution, least-privilege credentials, restricted network access, and audit logging.
Requirements
- A master’s degree in a computational STEM field, or a bachelor’s degree with at least 2 years of industry experience.
- Strong Python engineering skills and experience building and maintaining production-quality software.
- Hands-on experience with LLM APIs such as Claude or GPT and agentic patterns including tool use, orchestration, and multi-step reasoning.
- Familiarity with biomedical or chemical data sources and formats such as PDB, UniProt, ChEMBL, SDF/MOL, or FASTA.
- Understanding of data engineering fundamentals including ETL design, data validation, and structured and unstructured data at scale.
- Hands-on experience with Python testing frameworks, including pytest fixtures or parametrization.
- Preferred experience with agent orchestration frameworks and evaluation harnesses for LLM-generated code.
- Preferred familiarity with AWS, Docker, or Kubernetes and workflow orchestration.
- Preferred knowledge of multimodal biomedical data, large-scale ML dataset construction or curation, and agent security practices such as sandboxing, scoped credentials, and prompt injection mitigation.
Benefits
- Company-paid healthcare, flexible spending accounts, voluntary life insurance, 401(k) matching, and uncapped vacation.
- Work at Iambic’s state-of-the-art San Diego facility with an onsite gym and dining.
- The role offers an opportunity to work on a longer-term natural-language orchestrator for drug discovery and data analysis workflows.
Tech Stack
Categories
AI ApplicationsData Engineering
About Iambic Therapeutics, Inc
Iambic is a clinical-stage life sciences & technology company developing novel medicines using its AI-driven platform. Based in San Diego and founded in 2020, Iambic has assembled a world-class team that unites pioneering AI experts and experienced drug hunters. The Iambic platform has demonstrated delivery of new drug candidates to human clinical trials with industry-leading speed and across multiple target classes and mechanisms of action. Iambic is advancing a disease-agnostic pipeline of potential best-in-class and first-in-class medicines to address urgent unmet patient need. Learn more at iambic.ai