ML Research Scientist (MLRS) - Representation Learning for Molecular AI
Achira · San Francisco Office
About this role
## ML Research Scientist (MLRS) — Representation Learning for Molecular AI ### Why Achira At Achira, we’re building a frontier lab for **Physical AI for molecules**—developing world models for the physical microcosm. Our goal is to make biology at the molecular level something that can be **learned, predicted, and designed**. You’ll work at frontier scale across **massive compute, massive data, and massive ambition**, owning impactful work end-to-end—from **ideation and architecture** to **deployment on distributed infrastructure**. ### About the Role We’re seeking **deep learning researchers** to build rich representations of **atomistic systems** to teach AI about the microscopic world. You’ll collaborate with **domain experts in molecular modeling** to develop Achira’s next-generation **foundation models**, working across: - **Model architecture** - **Data** - **Training strategy** …to explore new points on the Pareto frontier of **representational richness, robustness, accuracy, and speed** for microscale world models. **Location / Work model:** - Prefer **San Francisco** (hybrid) - Highly skilled candidates may be considered for **New York City** with travel to San Francisco as needed - Hybrid roles require spending at least some time in the office for collaboration - **Travel** is part of all roles (conferences and corporate on-site activities) ### What You’ll Do - Build a robust **pre-, mid-, and post-training curriculum** to ensure foundation model performance and impact - Create **reinforcement learning strategies** to focus model capacity where it matters most, especially when training data doesn’t cover the domain of applicability - Develop expressive representations of **molecular and atomistic structure and dynamics**, including: - **Equivariant graph neural networks** - **Geometric transformers** - **Latent encoders** capturing physical symmetries and constraints - Prototype, benchmark, and iterate rapidly to turn research ideas into reusable, scalable components across Achira - Collaborate with **physicists and chemists** to ensure models are grounded in real physics - Work with **research engineers and the infrastructure team** to identify where research needs support to deliver effective results ### About You - Drive to apply modern ML techniques to solve problems at the frontier of the microscopic world - Willingness to follow the data and embrace an empirical approach - Pragmatic approach to **inductive bias** (e.g., physical priors, equivariance) - Experience designing, running, and analyzing ML experiments at scale - Experience with **3D geometric deep learning** - ML researcher with professional experience (post-degree) in an industry setting - Demonstrated research impact via conference talks/publications, open-source contributions, or released models - Strong interdisciplinary communication and presentation skills (able to translate ideas to non-ML colleagues) - Proficiency in **Python** and modern ML frameworks (**PyTorch, JAX**) - Experience collaborating on research projects across multi-person teams - Desire and comfort working on frontier problems in physical AI ### Nice to Have - Self-supervised representation learning experience - Bayesian deep learning and uncertainty quantification - Generative models for 3D systems - Experience with equivariant GNN architectures (e.g., **NequIP, MACE, SchNet, PaiNN**, or similar) - Prior experience in computational chemistry, biology, or materials science
Listing freshness
CronJobs last confirmed this listing 6d ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.