AI Researcher

Talus Bio • Seattle, WA

1d • $140 - $210 • Onsite

About The Position

Talus Bio is hiring an AI Researcher to work full-time, in person at its Seattle office. The role is in a small, early-stage preclinical biotechnology company developing AI models for drug discovery. The researcher will improve Ptarmigan, Talus Bio’s structure-free model for predicting compound-protein engagement across the human proteome, and develop new models for internal drug discovery programs and partners. Ptarmigan learns from the company’s chemoproteomics data, comprising hundreds of millions of compound-protein measurements collected in native human cells, including measurements for proteins without good structures.

The researcher will collaborate with multidisciplinary scientists to select models, metrics, and features, and work with the Product and Applications Lead to understand partner needs. The work focuses on practical impact in discovery and molecule optimization, not only in-silico metrics. The level will be set as AI Researcher or Senior AI Researcher based on experience.

The position involves developing and evaluating machine learning models, working with experimental scientists on prospective validation and active learning, building model-enabled tools and agents, and taking research models into production using cloud training and inference infrastructure. The researcher will present work internally and to partners, and may publish papers, preprints, and open-source software where appropriate. Applicants must be legally authorized to work in the United States.

Requirements

• Ph.D. in machine learning, computer science, computational chemistry, bioinformatics, or a related field plus at least 2 years of industry or postdoctoral experience; alternatively, an M.S. plus at least 5 years of industry experience.
• Experience applying machine learning to small molecules or protein-ligand interactions in a drug discovery setting.
• Experience designing and training deep learning models on molecular or protein data using PyTorch or a similar framework.
• Fluency in Python and Git, and experience training models on GPUs in the cloud.
• Ability to explain models, results, and limitations to chemists, biologists, and other non-computational colleagues.
• Experience building software and managing projects using agentic AI tools such as Claude Code or OpenAI Codex.
• Ability to work onsite in Seattle.
• Must be legally authorized to work in the United States.

Nice To Haves

• Experience building models used in a preclinical program for hit discovery, hit-to-lead, or lead optimization.
• Experience with generative models for small molecules, such as diffusion, flow matching, or chemical language models.
• Experience building protein language models or structure-based models, such as Boltz, AlphaFold, or docking.
• Experience with proteomics, mass spectrometry, or chemoproteomics data, including activity-based protein profiling.
• Experience building custom LLM agents or tools using the Model Context Protocol (MCP).
• A record of publications or open-source software in machine learning for biology or chemistry.
• Experience with active learning, uncertainty estimation, or Bayesian optimization.
• Experience leading machine learning projects or mentoring other scientists.

Responsibilities

• Develop architectures, training objectives, and data representations to improve Ptarmigan’s predictions of compound-protein engagement.
• Build protein-ligand interaction and generative chemistry models for hit discovery, hit-to-lead campaigns, and lead optimization, particularly for targets lacking structures or known binding pockets.
• Design benchmarks, held-out splits, and baselines that reflect practical model use; evaluate performance and report limitations and failure cases.
• Collaborate with experimental scientists to select compounds and experiments for prospective validation and active learning.
• Build tools and agents that call models through APIs and MCP so scientists and AI agents can run virtual screens and interpret results.
• Write tested, version-controlled code and take models from research to production, collaborating on cloud training and inference infrastructure.
• Present plans and results at R&D meetings and to partners, and publish papers, preprints, or open-source software where it advances the science.

Benefits

• Medical, dental, and vision insurance with 100% company-paid premiums for employees and 60% company-paid premiums for dependents.
• Commuter and transportation reimbursement program.
• 401(k) plan with a Talus Bio contribution regardless of employee contribution.
• Basic life and AD&D insurance with 100% company-paid premiums.
• Short- and long-term disability insurance with 100% company-paid premiums.
• Paid sick leave.
• Generous paid time off and holidays, including a paid end-of-year shutdown.
• Weekly meals, snacks, and drinks.
• Flexible working hours.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: Ph.D. or professional degree