5 months ago
San Francisco, CA, USA or New York, NY, USASenior
Responsibilities
- Design and run experiments for foundation model development
- Engineer evaluation metrics that enable rapid model iteration
- Build and maintain scalable, reproducible libraries for training, experimentation, evaluation, and simulation
- Implement model architectures from published research and in collaboration with in-house researchers
- Enable agent-driven research workflows and maintain guardrails for agentic tooling
- Prepare manuscripts, software artifacts, and datasets for public release
- Scale machine learning systems, train and evaluate models, and turn scientific prototypes into production systems
Requirements
- Strong software engineering fundamentals, including reproducible research pipelines, documentation, and coding best practices
- Observable work artifacts such as GitHub projects or papers involving machine learning or scientific computing libraries
- Working knowledge of PyTorch, JAX, and the modern machine learning research stack
- Comfort with HPC or large-scale compute environments and running hundreds or thousands of experiments concurrently
- Scientific depth sufficient to engage with molecular simulation research questions, developed through industry experience or a PhD
- Experience with equivariant architectures, geometric deep learning, or graph neural networks is preferred
- Familiarity with diffusion models, flow matching, or score-based methods is preferred
- Open-source involvement in machine learning or scientific computing libraries is preferred
- Experience building agent-driven research, active learning, or data curation pipelines is preferred
Benefits
- Hybrid work arrangement in San Francisco or potentially New York City with travel to San Francisco as needed
- Travel to conferences and corporate on-site activities
Tech Stack
Categories
AI ResearchML Engineering
About Achira
Achira builds atomistic foundation simulation models that simulate molecular interactions to support drug discovery and preclinical research for biotech and pharmaceutical teams. The privately held company, founded in 2024 and based in San Francisco, offers its technology as software and research collaborations. Its work combines AI with large-scale physics-based simulation to accelerate target validation and lead optimization.