Autonomous Bayesian Experiment Designer

Lila Sciences, Inc.; Cambridge, San Francisco (MA, CA); On-site; USD 34,000 - 62,000; Full time

Job summary

Lila Sciences seeks a Co-Op in Bayesian Methods for Complex Decision Making in Cambridge, MA. You will collaborate with research scientists and engineers to design Bayesian strategies for experiment selection and autonomous discovery agents, using Gaussian processes, Bayesian optimization, and probabilistic modeling.

Work will involve evaluating methods on live campaign data, communicating results to ML and experimental teams, and potentially contributing to publications.

Qualifications

• Pursuing a Master’s or PhD in statistics, ML, CS, operations research, applied math, or a quantitative science.
• Solid grounding in Bayesian inference and decision making (priors and posterior predictive distributions).
• Experience with Gaussian processes, Bayesian optimization, bandits, reinforcement learning, or probabilistic modeling.
• Strong Python skills with PyTorch and probabilistic libraries (Pyro, PyMC, BoTorch).

Responsibilities

• Design and benchmark Bayesian experiment-selection strategies under realistic budgets.
• Build autonomous discovery agents that propose next experiments from surrogate models.
• Develop in-context learning approaches inspired by Bayesian inference and evaluate calibration/robustness.
• Run retrospective and live evaluations on active campaign data with clear baselines and metrics.
• Present findings to ML and experimental teams, with potential for publication.

Skills

Bayesian inference

Posterior distributions

Gaussian processes

Bayesian optimization

Bandits

Reinforcement learning

Probabilistic programming

Python (PyTorch)

Pyro

PyMC

BoTorch

Communication

Education

Master's or PhD in statistics / ML / CS / OR / applied math

Tools

PyTorch

Pyro

PyMC

BoTorch

Job description

Lila Sciences seeks a Co-Op in Bayesian Methods for Complex Decision Making in Cambridge, MA. You will collaborate with research scientists and engineers to design Bayesian strategies for experiment selection and autonomous discovery agents, using Gaussian processes, Bayesian optimization, and probabilistic modeling.

Work will involve evaluating methods on live campaign data, communicating results to ML and experimental teams, and potentially contributing to publications.