Research Software Engineer

Job board
Job board

OpenADMET – Research Software Engineer

The Open Molecular Software Foundation (OMSF) is seeking a Research Software Engineer for the OpenADMET project (OpenADMET.org). This role is intended for a skilled computer programmer and debugger with a strong grounding in computer science. Experience with small molecules, drug discovery, or ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity) is strongly preferred. The Research Software Engineer will work closely with both technical and scientific teams to build and optimize software tools that accelerate open-source ADMET model development and deployment. This fully remote, grant-funded position has a minimum duration of 2 years, with the potential for extension based on funding availability.

The Research Software Engineer will collaborate with the distributed OMSF and OpenADMET teams, primarily based in Europe, Australia, and the United States, and may require occasional travel. This role will report directly to the tech or science lead.

About OpenADMET

OpenADMET (OpenADMET.org) is a new collaborative effort between the Open Molecular Software Foundation (OMSF), UCSF, Octant, and MSKCC to generate high-quality open ADMET datasets and open source models to accelerate small molecule drug discovery. Given that >90% of molecules synthesized in a small molecule discovery program fail to meet ADMET objectives, OpenADMET aims to produce open source models capable of greatly reducing time, cost, and failure rates in drug discovery and development programs due to ADMET issues. In addition to curating public ADMET data in ML-ready formats, OpenADMET will generate large targeted open experimental datasets (Octant) and X-ray/cryo-EM structural data (UCSF) that will power open source models (OMSF) and blind community challenges seeking to advance the state of the art. OpenADMET is funded by a variety of sources, including ARPA-H and the Gates Foundation.

Key Duties and Responsibilities

Software Development and Debugging

  • Write clean, efficient, and well-documented code to support the development of ADMET modeling pipelines.
  • Troubleshoot and debug existing codebases used for molecular data processing and machine learning applications.
  • Develop new features or modules that integrate external libraries and computational tools to advance the utility and performance of ADMET workflows.

Computational Infrastructure and Tooling

  • Collaborate with the ML Infrastructure and Scientific teams to ensure software tooling aligns with scientific goals and best coding practices.
  • Contribute to continuous integration (CI) and deployment (CD) pipelines for automating software testing, building, and release processes.
  • Assist in configuring and optimizing cloud-based or local HPC systems for large-scale computational tasks, including parallelization and job scheduling.

Data Handling and Integration

  • Work with Data Curation teams to refine data ingestion and standardization workflows, ensuring high-quality data for downstream modeling.
  • Implement and maintain data transformation pipelines that enable efficient training and inference for ADMET models.
  • Aid in identifying and resolving data inconsistencies or integration challenges to preserve data integrity throughout the pipeline.

Scientific Collaboration

  • Interact with scientists and computational researchers to translate research objectives into robust software solutions.
  • Provide technical guidance on using computational frameworks and libraries (e.g., RDKit, Pytorch, DeepChem, or similar) for small molecule analysis.
  • Maintain close communication with cross-functional teams, including the Tech Lead for ML Infrastructure, to align development efforts with project goals.

Documentation and Open-Source Contributions

  • Produce clear, concise documentation for developed software tools, libraries, and pipelines.
  • Follow open-source best practices when contributing to repositories (version control, code reviews, issue tracking).
  • Collaborate with the community to address software issues, requests, and enhancements, fostering a transparent and collaborative environment.

Qualifications:

  • Advanced degree in Computer Science, Software Engineering, Computational Chemistry, or a related field; equivalent practical experience also considered.
  • Demonstrated experience in software development (Python strongly preferred) and debugging in a research or scientific context.
  • Familiarity with best practices in version control (Git), CI/CD, containerization (e.g., Docker), and automated testing.
  • Knowledge of fundamental concepts in small molecule drug discovery or computational chemistry (e.g., molecular descriptors, ADMET principles) is strongly preferred.
  • Ability to troubleshoot complex workflows in distributed or cloud-based computing environments.
  • Excellent communication and problem-solving skills, with an ability to collaborate effectively in a remote, interdisciplinary environment.

Preferred Qualifications

  • Experience with molecular data processing and modeling libraries (e.g., RDKit, DeepChem).
  • Familiarity with machine learning frameworks (e.g., PyTorch, TensorFlow) and scientific computing libraries (NumPy, SciPy, etc.).
  • Background in ADMET data or drug discovery pipelines.
  • Knowledge of FAIR data principles and open-source scientific software development.
  • Experience contributing to or maintaining open-source repositories.

Compensation

This is a full-time, fixed contract position with an expected gross salary range of $80,000-$100,000, depending on qualifications, experience, and location. OMSF offers standard benefits, including healthcare, retirement contributions, paid time off, and other employer contributions per local regulations. Salary will be negotiated in the local currency and may vary by location due to differences in mandatory employer contributions.

Location

OMSF is a fully remote organization. For this role, we will accept only applications from candidates who are based in the US due to federal funding restrictions.

Application Process

Please apply using this form.

Any additional queries about the role and OMSF can be sent to careers@omsf.io.