Co-Op, AI Nucleic Acid Design

Lila Sciences • San Francisco, CA

4d • Onsite

About The Position

Lila Sciences is building scientific superintelligence by combining large-scale automated experimentation with frontier machine learning. The Life Science AI (LSAI) function researches automated reasoning on biological data, bringing together state-of-the-art machine learning and breakthrough biology.

This six-month co-op is with Lila’s Nucleic Acid Design team within LSAI. The team develops models and design strategies for RNA and DNA sequences. The co-op focuses on open-ended research that could shape future approaches to nucleic acid sequence design, including UTR design, regulatory element design, and the use of large reasoning models for scientific discovery. The co-op researcher will own a defined research project with mentorship from ML scientists and will work closely with experimental scientists to connect models to biological data.

The role is intended for someone curious, comfortable with open-ended problems, and eager to learn about machine learning and the biology behind sequence-to-function modeling. It is a full-time, six-month co-op term onsite in San Francisco.

Requirements

• Currently enrolled in an MS or PhD program in machine learning, computational biology, bioengineering, computer science, statistics, or a related quantitative field.
• Hands-on experience building and training machine learning models.
• Strong Python skills and experience with PyTorch, JAX, or a similar framework.
• Coursework or research experience with biological sequence data, such as DNA or RNA.
• Curiosity about nucleic acid biology, such as RNA biology, gene regulation, or sequence-to-function relationships.
• Available for a full-time, six-month co-op term onsite in San Francisco.

Nice To Haves

• Experience with sequence-to-function models, genomic language models, or models trained on MPRA, reporter assay, or other functional genomics data.
• Familiarity with RNA secondary structure prediction, UTR or codon design, or inverse design methods.
• Experience with generative modeling, active learning, or Bayesian optimization.
• Exposure to wet-lab data or collaboration with experimental scientists.
• A research publication, preprint, or open-source project in machine learning or computational biology.
• Experience using or building with large language or reasoning models, AI agents, or LLM-based tools for scientific tasks.

Responsibilities

• Lead a scoped research project in nucleic acid sequence modeling or design.
• Build machine learning models on RNA and DNA sequence-function data, including prototyping methods for property prediction, generative design, or candidate selection.
• Investigate model behavior and propose biological hypotheses about why sequences succeed or fail.
• Explore how large reasoning models can support scientific discovery and sequence design, including generating hypotheses, reasoning over experimental results, or guiding design choices.
• Collaborate with experimental scientists to understand assays and propose experiments that test new ideas.
• Present findings to the team and contribute to research write-ups and, where possible, external publications or presentations.

What This Job Offers

• Job Type: Full-time
• Career Level: Intern