Machine Learning Scientist

Iambic Therapeutics, Inc•San Diego, CA

1d•Remote

About The Position

We are seeking a Machine Learning Scientist to join Iambic Therapeutics and work on transformer-based diffusion methods for the prediction of biomolecular structure. In this role, you will develop generative models that operate over tokenized structural representations, contributing to the next generation of our core ML technologies including NeuralPLexer and Enchant. This work sits at the intersection of generative modeling, structural biology, and representation learning. You will design and train structure tokenizers, build diffusion models over learned token spaces, curate and process large-scale biomolecular datasets, and benchmark model performance against state-of-the-art methods, all in service of accelerating drug discovery. We are hiring across multiple levels (RS I, RS II, and Senior) and welcome candidates ranging from recent PhD graduates to experienced researchers with a strong publication or deployment record.

Requirements

PhD in machine learning, computer science, computational chemistry, physics, or a related computational STEM field, or equivalent industry experience demonstrating comparable depth
Strong Python and PyTorch skills, including end-to-end implementation and training of deep learning models
Demonstrated experience in one or more of the following: 3D atomistic or molecular modeling Vector quantization and learned discrete representations Diffusion, flow-matching, or related generative modeling in continuous vector spaces
Strong engineering practices: reproducible experimentation, clean code, testing, and performance-aware debugging
Comfort with modern ML infrastructure (e.g., Docker, CUDA, Kubernetes, experiment tracking tools such as Weights & Biases)
RS II and Senior candidates are expected to bring industry experience applying ML methods to drug discovery or related scientific domains
Senior candidates are expected to have a track record of independently driving research direction and mentoring others

Nice To Haves

Experience with discrete diffusion, masked generative or transfusion models
Protein–ligand modeling, structure prediction, or structure-based drug discovery
Geometric deep learning and/or equivariant architectures
Multi-GPU / distributed training at scale
Docking, molecular dynamics, or other biomolecular simulation methods

Responsibilities

Design, implement, and train discrete and continuous diffusion models for predicting biomolecular structure tokens
Develop and iterate on structure tokenizers, including vector-quantized representations of 3D molecular and protein structure
Build and maintain data processing pipelines for large-scale biomolecular structure datasets
Train models on multi-GPU clusters, managing large-scale training runs
Develop rigorous benchmarking and evaluation workflows; validate against external benchmarks while prioritizing internal discovery-relevant metrics
Collaborate with ML scientists, computational chemists, and drug discovery teams to integrate models into discovery workflows
Communicate results to internal teams, external partners, and at scientific conferences
Mentor interns and junior team members through code reviews, technical guidance, and best practices (Senior level)