Lead Computational Scientist (Computational Physics & Machine Learning)

About Us

Grafton Biosciences is a San Francisco-based biotech startup focused on solving disease through groundbreaking innovations in early detection and therapeutics. We are combining cutting-edge synthetic biology, machine learning, and manufacturing to fundamentally extend healthy human lifespans. We’re looking for passionate team members who want to shape the future.

The Role

As the Lead Computational Scientist, you will own the design, implementation and validation of our machine‑learning force‑field: a differentiable, sub‑millisecond physics engine that provides the energy and force evaluations driving every stage of the platform—from generative design to in‑silico screening and active learning.

Key Responsibilities

• Architect a long‑range‑aware ML force‑field (e.g., dot‑product or equivariant GNN with PME / polarisation) that scales linearly to multi‑kilodalton complexes.
• Define, generate and curate a 2 M‑frame quantum‑mechanical training set (DFT / DLPNO‑CCSD(T)) using active‑learning workflows.
• Deliver production‑grade CUDA/Triton kernels achieving ≤ 0.3 ms forward backward latency on NVIDIA H100 GPUs.
• Build an automated stability and drift‑validation suite (energy conservation, long‑timescale MD) and own pass/fail gates for every new model checkpoint.
• Collaborate closely with machine‑learning and wet‑lab teams to ensure seamless coupling between physics models, generative algorithms and experimental feedback loops.

Minimum Qualifications

• PhD (or equivalent industry experience) in Computational Chemistry, Chemical Physics, Machine Learning, or related discipline.
• 5 years hands‑on development of physics‑based ML models (e.g., TorchMD‑Net, MACE, NequIP, Orb) and molecular‑dynamics kernels.
• Demonstrated ability to deliver a force‑field used by external groups or in production pipelines.
• Fluency in PyTorch, CUDA and/or Triton; strong software‑engineering skills (testing, version control, CI).
• Track record of accelerating MD or MLFF inference to sub‑millisecond latency or scaling training on multi‑GPU clusters.
• Excellent communication skills—able to explain trade‑offs to both ML engineers and experimental biologists.

Preferred Qualifications

• Experience incorporating long‑range interactions or polarisation effects into ML‑based force‑fields or hybrid simulation workflows.
• Hands‑on involvement with active‑learning pipelines and high‑throughput quantum‑chemistry calculations.
• Previous leadership role in a cross‑functional setting (start‑up or large‑scale research collaboration).
• Familiarity with biomolecular physics.

What We Offer

• Competitive salary ($170 k – $280 k, DOE).
• Comprehensive health, dental and vision coverage.
• Flexible, hybrid work environment and generous PTO.
• Annual professional‑development budget.
• A chance to shape a cutting‑edge therapeutic platform from the ground up—working alongside experts in machine learning, molecular biology and drug discovery.

How to Apply

Submit your résumé, a link to relevant publications or code repos, and a brief note on why you are a good fit for this role. If there is a fit, we will reach out within 2 days and decisions will be made within 1 week.

Job Type: Full-time

Pay: $170,000.00 - $280,000.00 per year

Benefits:

• 401(k)
• Dental insurance
• Health insurance
• Paid time off
• Vision insurance

Application Question(s):

• Why are you a fit for this role?
• How soon can you begin?

Ability to Commute:

• San Francisco, CA 94108 (Required)

Work Location: In person

Salary : $170,000 - $280,000