Machine learning · Biophysics · Molecular Design

Talal Widatalla

San Francisco, CA

PhD candidate in Biophysics at Stanford and the Arc Institute, advised by Brian Hie. I build and apply machine learning systems for molecular design. I'm currently working on LLM post-training as an ML Scientist Co-op at Lila. Previously, I worked on protein generative models at Generate Biomedicines and ML for drug discovery at Merck.

I'm especially interested in imbuing biophysical and experimental information into biological generative models for drug discovery and optimization, with a growing interest in agentic lab-in-the-loop design.

Scholar LinkedIn X GitHub Email
Talal Widatalla

Always happy to chat. Just email me at talal.widatalla@gmail.com.

Selected work

* Denotes equal contribution
First & co-first author
Co-author

Experience

SEP 2026 – PRESENT

Machine Learning Scientist Co-op

Lila Sciences

LLM post-training

JAN 2024 – PRESENT

Graduate Researcher, Brian Hie Lab

Stanford University & the Arc Institute

Aligning protein generative models to experimental fitness with RL, applied to vaccine optimization (ProteinDPO), diffusion models for full-atom protein sequence design (FAMPNN), the first open-source framework for single-shot and low-N de novo antibody design (Germinal), and other cool projects yet to be released!

JUN – SEP 2025

Machine Learning Intern

Generate Biomedicines

Worked on training of diffusion-based protein generative model for improved enzyme and binder design.

AUG 2022 – JUN 2025

AI/ML Data Scientist

Merck Research Laboratories

Built production ML systems combining GNNs, language models and molecular dynamics simulations for antibody property prediction, and a high-throughput small molecule virtual-screening pipeline using active learning and structural deep learning.

MAY – AUG 2022

Scientific Software Development Intern

OpenEye Scientific Software

Developed software for mining structural properties from PDB structures to guide structure-based ligand design.