Machine Learning Engineer, Model Experimentation

Aether Biomachines•South San Francisco, CA

15h•$150,000 - $200,000

About The Position

Aether is hiring a Machine Learning Engineer to rapidly test modeling ideas and provide evidence-based recommendations on which approaches warrant further work. The role is part of a small, senior ML team, and its core purpose is to run a fast experimental loop: establish a baseline, test a model or training change, evaluate the results, and clearly recommend whether to continue, change course, or stop. Most ideas are expected not to work; success is measured by how quickly and clearly the role helps determine which ideas hold up. The engineer will work day to day with senior ML team members, who help set priorities and review experimental conclusions. The work uses data from real lab measurements, allowing model results to be checked against observed bench outcomes. The role also involves working within Aether's ML infrastructure and improving it when it slows experimentation. Aether engineers enzymes to make materials that are difficult or impossible to produce by other means. Its print materials are shipping into defense and unmanned systems, and it is developing protein-material binding data for models that can identify proteins capable of making a desired material. No chemistry or biology background is required; Aether will teach the molecular and protein domain, its data, and its tooling.

Requirements

Hands-on experience training and evaluating models, gained through research, employment, competitions, or serious personal projects.
Strong experimental habits, including establishing baselines first, changing one thing at a time, using ablations, and evaluating honestly.
Ability to work quickly and write code that runs promptly, cleaning it up after an idea proves worthwhile.
A track record of stopping experiments or projects when evidence indicates they should be abandoned, and explaining what prompted the decision and how quickly it was made.
Clear written communication of results, especially negative results.
Fluency in Python and a modern deep learning framework such as PyTorch or JAX.

Nice To Haves

Experience with world models or latent-prediction methods, such as JEPA or DreamerV3.
Experience with diffusion models in any domain.
Competition results, open-source contributions, or a project built and maintained independently.

Responsibilities

Design and run end-to-end ML experiments, including baselines, model changes, training runs, and evaluation.
Make a clear decision for each experiment and document it in a page or less, including experiments that fail.
Build evaluations that can be trusted even when their results contradict the idea being tested.
Bring ideas from the wider field, such as world models, latent-prediction objectives, or diffusion, and test them against Aether's data.
Work within the team's ML infrastructure and improve it where it slows experiments down.