Jobs at Lila Sciences

Develop and apply machine learning methods for protein engineering, including generative design, property prediction, candidate selection, active learning, and sequence or structure modeling. Collaborate with experimental scientists to translate biological objectives into computational problems, evaluate model generalization, interpret wet-lab results, and improve design-test-learn workflows for therapeutic biomolecules.

Develop BioML systems that encode and evaluate mechanistic biological reasoning. Analyze single-cell, perturbation, proteomics, imaging, and genetic data; design experimental campaigns; build outcome-verifiable benchmarks; and connect computational predictions with experimental decisions. The role requires rigorous evidence assessment, uncertainty interpretation, reproducible analysis, and collaboration with ML engineers, experimental scientists, and platform teams.

Design therapeutic proteins for active biologics programs, translating biological constraints into machine learning hypotheses. Build reasoning and orchestration systems for drug discovery, develop benchmarks and evaluation infrastructure, and improve reproducibility, throughput, and inference efficiency. Collaborate with domain scientists and AI researchers to convert expert judgment into ML objectives and scalable platform capabilities. The role requires strong software engineering, evaluation rigor, biological intuition, and expertise in protein sequence, structure, and function.

Leads computational protein engineering initiatives using generative and predictive machine learning to design therapeutic biomolecules. Owns workflows from design specification through wet-lab validation and active learning, develops sequence- and structure-based models, builds evaluation frameworks, and integrates protein design methods into autonomous science software. Collaborates with experimental scientists, AI researchers, and platform teams to interpret results and improve biomolecular design strategies.

Build and improve applied AI models for scientific customer workflows. Responsibilities include model post-training, evaluation loop development, experiment design, debugging model behavior, and integrating AI capabilities into production software. The role collaborates with AI researchers and software engineers to adapt models, create reusable tooling, and translate customer feedback into model improvements.

The Machine Learning Engineer will design and implement ML pipelines and productionize models, collaborating with scientists and engineers on scalable systems.

Lead an 8–10-person engineering team building LILA’s AI-native application platform, including chat, agents, artifacts, and integrations with laboratory workflows and ML pipelines. Define technical strategy, oversee end-to-end product delivery, ensure reliability and security, collaborate with scientists and cross-functional partners, mentor engineers, and represent the company’s applied-AI work externally.

Design and build high-performance UI and APIs, manage database architecture, optimize systems for reliability and performance, and collaborate cross-functionally in a scientific context.

Lead training, adaptation, evaluation, and productionization of Lila's AI models for scientific customer workflows. Build evaluation loops, design experiments, debug model failures, integrate model improvements into product workflows, and create reusable tooling for model adaptation, evaluation, and deployment while collaborating across research and software teams.

Develop and integrate ML models for RNA and DNA sequence design (UTRs, CDS, promoters/enhancers). Create generative, prediction, and active-learning methods; partner with experimental teams to design assays and validate sequences; investigate biological mechanisms and translate insights into improved models and platform capabilities; publish or share research externally.

The Senior Software Engineer will develop systems for scientific workflows, APIs, and applications, collaborating across teams to enhance performance and reliability in production environments.

The Staff Engineer will lead technical direction on data infrastructure, focusing on ingestion frameworks, storage architecture, and orchestration to support scientific workflows. Responsibilities include mentoring, ensuring reliability, and collaborating with cross-functional teams to establish coding standards and data integrity.

The Technical Program Manager will lead AI data generation projects, ensuring consistent quality and efficient execution while communicating across teams.

Lead the development and strategy of Lila Sciences' software products, focusing on integrating AI within scientific workflows and managing high-performing teams.

The Principal Software Engineer will design and build APIs, optimize database architecture, enhance performance, and collaborate on cloud infrastructure for scientific applications.

This role invites interested candidates to join a talent community for future job opportunities at Lila.

Lead design and delivery of enterprise-grade platform capabilities: multi-tenancy, identity and authorization, tenant provisioning, metering/billing, audit/compliance, and automation. Act as a hands-on principal engineer across platform, security, and AI/ML teams to build scalable, secure, and operable systems for regulated scientific customers.

Lead small-molecule discovery programs end-to-end, ensuring the autonomous platform delivers high-quality clinical candidates. Set throughput, quality, and timeline targets; integrate AI/ML and experimental teams; define assay cascades and decision criteria; manage external CRO relationships; and translate platform capabilities for partnerships and leadership updates.

Lead the development and integration of advanced safety systems for scientific AI applications, building a team and establishing a research strategy.

As a Product Lead for Software/Applied AI, you will own specific product areas, guiding full-stack product execution and cross-functional collaboration to build impactful scientific tools.