Biological Structures Data Engineer I/ii

Iambic Iambic · Pharma · Boston, MA · Technology

Seeking a Biological Structures Data Engineer to build and maintain data pipelines for acquiring, curating, and transforming experimental and synthetic structural data for training AI models in drug discovery. This role requires deep fluency with structural biology data formats and strong software engineering practices to create robust, reusable infrastructure.

What you'd actually do

  1. Understand, maintain, and enhance existing data pipelines, including parsing and validation of structural data (.cif/PDB and beyond)
  2. Integrate and adapt data from a range of public and proprietary sources into reliable, reusable pipelines
  3. Work closely with ML scientists to ensure their data needs are met
  4. Ensure all data is stored in a secure, robust, and retrievable manner
  5. Perform code reviews and exemplify software engineering best practices.

Skills

Required

  • PhD or equivalent experience in Bioinformatics, Computational Biology, Cheminformatics or a related field
  • Hands-on familiarity with structural biology data — .cif files, the PDB, and the practical challenges of working with real-world molecular structures
  • Strong software engineering practices, with a focus on maintainable, well-tested systems
  • Proficiency in Python
  • Comfortable operating in a research-driven environment; developing, learning, and adapting cutting edge technologies
  • Strong collaboration skills and the ability to communicate across a cross-functional research and engineering team

Nice to have

  • 3+ years of relevant experience (for Engineer II)
  • Experience designing data pipelines or data infrastructure for heterogeneous or large-scale datasets
  • Familiarity with additional drug-discovery-relevant data types
  • Experience contributing to a data lake or comparable centralized data platform
  • Familiarity with auxiliary data or data transformations relevant to protein structure prediction
  • Exposure to cloud-based systems (e.g., AWS, Kubernetes) and/or HPC
  • Background bridging science and software engineering

What the JD emphasized

  • structural data
  • structural biology data
  • computational Biology
  • Cheminformatics

Other signals

  • train the next generation of NeuralPLexer models
  • structural data
  • prepare experimental structural (e.g., protein–ligand complexes) and affinity data for training
  • create and ingest large volumes of high-quality computationally generated synthetic data