Lila Sciences

Small

Lila Sciences is a startup applying artificial intelligence to scientific research, aiming to build a platform that accelerates discovery across fields such as life sciences, chemistry, and materials science. It is known for pioneering the concept of an AI-driven 'scientific superintelligence' to autonomously generate and test hypotheses.

4 interview notes · updated Jul 2026

Lila Sciences·Software Engineer·Technical Phone Screen

Jun 2026

Interviewed for the AI Resident role at Lila Sciences. The technical depth they expected was no joke. One question basically ate up the whole session and I left feeling like I'd only scratched the surface.

How do you quantify uncertainty in an active learning pipeline aimed at data efficiency, specifically when trying to cover a large phase space while minimizing expensive DFT calculations? Walk through uncertainty estimators, acquisition functions, and how you balance diversity against uncertainty.

“This one sprawled fast.”

View Post

Lila Sciences·Software Engineer·Technical Phone Screen

May 2026

Research engineer interview at Lila Sciences focused heavily on LLM-driven scientific automation, specifically around atomic manipulation and crystal structure tasks. The technical depth surprised me a bit, less coding and more conceptual design around AI systems for physical science.

How would you use LLMs to drive automation in experimental or atomic manipulation workflows, and what are the key limitations you'd need to address?
How would you introduce causal reasoning and physical constraints into an LLM-based agent that operates in a scientific domain?
How would you design an evaluation benchmark to assess whether an AI agent can reason logically about crystal structure operations?

“This is where I stumbled a bit.”

View Post

Lila Sciences·Software Engineer·Technical Phone Screen

Apr 2026

Research-heavy interview for the AI Resident role at Lila Sciences, focused almost entirely on ML force fields. Two meaty technical questions with an expectation that you can go deep on both the theory and the messy practical side of training these models.

When designing an ML force field model, how do you decide between building a specialist model for a narrow domain versus a generalist model that covers a broader chemical space?
How would you correct for systematic energy prediction bias when your ML force field encounters non-equilibrium configurations during inference?

“This one tripped me up more than I expected.”

View Post

Lila Sciences·Software Engineer·Technical Phone Screen

Apr 2026

Technical screen at Lila Sciences for a Research Engineer role. The whole conversation basically lived inside one question about DFT and how your choice of XC functional ripples through to MLIP quality. Dense material, and I wasn't fully warmed up for how deep they wanted to go on the cost-accuracy tradeoffs.

When generating DFT training data for machine-learning interatomic potentials, how does the choice of exchange-correlation functional (LDA, GGA/PBE, meta-GGA, hybrid) affect data quality and consistency, and how do those tradeoffs in cost versus accuracy carry forward into the downstream MLIP?

“This one took me a minute to frame properly.”

View Post