Software Engineer Ii, Machine Learning Systems & Productization

Iambic Iambic · Pharma · Boston, MA · Technology

Software Engineer II, Machine Learning Systems & Productization at Iambic Therapeutics. This role focuses on engineering systems for drug discovery, co-developing and refining ML training and evaluation workflows with ML scientists. The engineer will translate research code into robust, scalable systems, build benchmarking systems, and contribute to productization without owning core model development or infrastructure.

What you'd actually do

  1. Work embedded with ML scientists to co-develop and refine model training and evaluation workflows
  2. Translate experimental research code into maintainable, well-structured, and reusable systems
  3. Build and expand benchmarking systems for running models on structural and affinity datasets, computing metrics, and supporting reproducible evaluation
  4. Enable rapid iteration by developing tooling and interfaces that expose new capabilities to researchers
  5. Contribute to the ongoing development and productization of NeuralPLexer

Skills

Required

  • 8+ years of software engineering experience (or equivalent), ideally in ML-adjacent or data-intensive environments
  • Strong Python skills and demonstrated rigor in software engineering practices (testing, versioning, code quality)
  • Experience working closely with ML practitioners or in research-driven environments
  • Experience building or supporting ML workflows, data pipelines, or evaluation systems
  • Ability to operate in partially defined, research-heavy environments and bring structure to evolving codebases
  • Strong collaboration skills and comfort with pair programming and iterative development

Nice to have

  • Experience with scientific or computational research environments
  • Familiarity with structural biology, chemistry, or molecular modeling workflows
  • Exposure to cloud-based systems (e.g., AWS, Kubernetes) and/or HPC
  • Experience working with large-scale or heterogeneous datasets

What the JD emphasized

  • 8+ years of software engineering experience (or equivalent), ideally in ML-adjacent or data-intensive environments
  • Experience building or supporting ML workflows, data pipelines, or evaluation systems
  • Ability to operate in partially defined, research-heavy environments and bring structure to evolving codebases

Other signals

  • co-develop and refine model training and evaluation workflows
  • Translate experimental research code into maintainable, well-structured, and reusable systems
  • Build and expand benchmarking systems for running models on structural and affinity datasets, computing metrics, and supporting reproducible evaluation