Minimum of two years of relevant industry experience.
Proficiency in PyTorch and JAX.
Ability to think in asynchronous primitives.
Strong opinion on library design with an emphasis on clean abstractions and consistency.
Demonstrated track record of well-documented code via platforms like GitHub.
General knowledge of scalable, reliable machine learning systems.
Responsibilities
Build and maintain multi-stage asynchronous workflows for data generation and evaluations.
Rationalize the design of machine learning systems and software architecture.
Identify and resolve blockers to ensure scalability of foundation models.
Serve as a liaison between research scientists and the infrastructure team.
Benefits
Hybrid work environment with flexibility for San Francisco or New York City locations.
Travel opportunities for conferences and corporate activities.
Collaborative team culture fostering innovation.
Opportunity to work on cutting-edge molecular machine learning projects.
Full Job Description
About the Role
We're looking for a rare individual who thrives at the intersection of machine learning systems architecture and distributed computing. You will help architect the future of molecular machine learning by enabling our scientific teams to flexibly conduct experiments at scale, pushing the boundaries of foundation simulation models.
While we prefer candidates willing to work from our San Francisco office, highly skilled candidates may be considered for working from New York City with travel to San Francisco as needed. Both locations are offered as hybrid roles, spending at least some of your time working from the office in collaboration with coworkers. Travel is part of all roles at Achira, both to conferences and corporate on-site activities.
What You'll Do
Build and maintain robust multi-stage asynchronous workflows for running data generation, training, and evaluations for our machine learning stack.
Rationalize machine learning systems design and software architecture.
Identify blockers and build solutions that scale to the size of foundation models.
Operate as the glue between research scientists and the infrastructure team.
About You
At least two years relevant industry experience.
Highly fluent in and enthusiastic about PyTorch and JAX.
Solid track record of observable artifacts (e.g., GitHub) showing clear, well-documented code.
ML generalist who knows what scalable, reliable ML systems look like.
Nice to Have
Even if you hit none of these bonus features, we encourage you to apply!
Experience with equivariant architectures, geometric deep learning, or GNNs (NequIP, MACE, SchNet, PaiNN, or similar), and/or ML-assisted drug discovery.
Experience building in declarative workflow orchestration frameworks like Flyte, Dagster, etc.
Lack of fear around interacting with quantum chemical scientists and their data pipelines.
