Senior Scientific Developer

Deep Origin

About The Position

Deep Origin is a biotech startup building an operating system for science that transforms how life science research is conducted. Led by Michael Antonov, co-founder of Oculus, and backed by Formic Ventures, we are redefining the infrastructure behind modern drug discovery. Our AI-driven platform enables scientists to accelerate discovery, reduce cost, and bring breakthrough innovations to life faster. As we scale, engineering excellence is a critical lever in advancing our mission to dramatically reduce disease and extend human healthspan. We are hiring a Senior Scientific Developer to help build and scale the computational science layer of our drug discovery platform. This is a hands-on role at the intersection of scientific computing and software engineering. You will design, implement, and operate production-grade tools and workflows used by medicinal chemists and computational biologists — from molecular docking and free-energy calculations to system preparation and structure-based design. You will work across our Python SDK, scientific workflow definitions, containerized compute functions, and the Julia packages that power our molecular simulation stack. You will have ownership of key scientific capabilities from design through deployment, with a high level of independence and direct impact on what researchers can run on the platform. Applicants must be authorized to work for any employer in the U.S. We are unable to sponsor or take over sponsorship of an employment Visa at this time.

Requirements

MSc or PhD in chemistry, chemical biology, bioinformatics, computational chemistry, or a closely related field — or equivalent industry experience with a strong scientific track record.
Deep domain knowledge in at least one of: medicinal chemistry, cheminformatics, structural biology, molecular simulation, or computational drug discovery.
Excellent Python skills — you write clean, tested, production-quality code and are comfortable building libraries and APIs, not just notebooks and scripts. In practice, that means: You have authored and maintained an installable Python package; publishing to PyPI is a strong plus. You work with modern packaging and environments (`uv`, `conda`, or `pixi`). Linting and type checking are part of your default workflow (`ruff`, `ty`). You have used Marimo (or similar reactive/reproducible notebook tools) for scientific exploration, demos, or documentation.
Strong Docker skills — you are comfortable containerizing scientific Python code for production, not just running pre-built images. In practice, that means: You know how to containerize Python scripts, packages, and dependencies into reliable images. You can write multi-stage Dockerfiles for complex build pipelines. You know how to trim image size (layer caching, slim base images, build-arg hygiene, and keeping runtime images lean).
Experience implementing scientific algorithms and workflows end to end, from prototype to deployed, maintainable software.
AI-assisted development — you use tools like Claude Code and Cursor fluently, and you have judgment about where they accelerate you and where scientific correctness demands human review.
Strong fundamentals in software engineering: testing, version control, debugging, and designing clear interfaces for complex scientific data.
Ability to read scientific literature and translate methods into working implementations.
Systematic problem-solving approach with a strong sense of ownership.
Ability to work both independently and collaboratively in a fast-moving startup.

Nice To Haves

TypeScript/JavaScript experience — our platform UI and some backend services use modern web stacks.
Experience with PostgreSQL or scientific data platforms (chemical structure storage, RDKit, etc.).
Contributions to open-source scientific software.
Experience at an early-stage startup shipping scientific product features quickly.
Substantial experience with Julia, especially for scientific computing, molecular dynamics, or high-performance numerical work.
Hands-on experience with Kubernetes and cloud-native deployment patterns.
Experience with Argo Workflows (or similar workflow orchestration) and Knative (or similar serverless/container platforms).
Familiarity with molecular simulation ecosystems: force fields, system preparation, alchemical free-energy methods, or MD analysis pipelines.

Responsibilities

Design, implement, and maintain scientific software for drug discovery: docking, free-energy perturbation (FEP), molecular dynamics, cheminformatics, and related computational biology workflows.
Build and evolve the Deep Origin Python SDK and scientific APIs that scientists use to run, monitor, and analyze platform workflows.
Develop and maintain Julia-based simulation and analysis packages for molecular systems (e.g., system preparation, MD/FEP protocols, post-processing).
Author and operate workflow definitions (Argo Workflows) and serverless scientific services (Knative) that orchestrate multi-step computational pipelines on Kubernetes.
Package scientific tools as reproducible, containerized functions with clear input/output contracts, validation, and integration tests.
Translate domain requirements from medicinal chemistry and computational biology into robust, scalable technical implementations.
Collaborate with platform engineering, product, and science teams to integrate scientific tools into our multi-tenant cloud platform.
Ensure scientific code quality through testing, documentation, benchmarking, and careful handling of edge cases in real-world molecular datasets.
Debug and resolve issues across the full stack — from numerical methods and force-field behavior to workflow failures in production.
Contribute to engineering best practices: code review, CI/CD, observability, and operational runbooks for long-running scientific jobs.
Mentor teammates and help raise the bar for scientific software engineering across the organization.