Co-op, Software, Applied AI Platform Engineer

Your Impact at LILA

Lila Sciences builds AI systems that accelerate discovery across the physical and life sciences. The Platform Engineering team owns the core infrastructure and developer-facing services that power Lila's AI Science Factory™ — including APIs, data pipelines, and the agentic systems that orchestrate scientific workflows at scale.

This co-op has two focus tracks. Candidates may be matched to one or both based on interest and fit:

Track 1 — Data Platform: Build pipelines and services that structure scientific knowledge (literature, patents, lab data) into signals that power Lila's AI models and applications.

Track 2 — Agentic SSR (AI and Server-Side Rendering): Build the server-rendered, agentic layer of the Lila Platform — the infrastructure that enables AI agents to compose and serve dynamic scientific interfaces at runtime.

In either track, you will ship production code, work alongside research scientists and ML engineers, and contribute to a platform that runs real scientific experiments.

What You'll Be Building

Data Platform Track

• Build and maintain ingestion and transformation pipelines for scientific literature, patents, and lab-generated data
• Implement structured data extraction workflows, including schema design, validation, and quality evaluation
• Integrate retrieval and RAG pipelines that surface relevant documents, tables, and figures to downstream Lila applications
• Generate and validate structured datasets; run end-to-end pipelines and analyze results against clear evaluation criteria
• Collaborate with research scientists to translate scientific domain requirements into robust data models
• Document findings and present results to the team; contribute to a publication or open-source project where the work supports it

Agentic SSR Track

• Build server-side rendering services and APIs that enable AI agents to compose and deliver dynamic scientific interfaces
• Implement agentic workflow primitives: task routing, context management, streaming responses, and tool integration
• Develop platform features end-to-end: schema design, business logic, API surface, and automated tests
• Instrument code for observability; participate in debugging and root-cause analysis of production issues
• Improve developer experience through internal tooling, reusable libraries, and documentation
• Contribute to technical design discussions and code reviews

What You'll Need to Succeed

• Pursuing a Bachelor's, Master's, or PhD in Computer Science, Software Engineering, or a related field
• Strong foundation in software engineering fundamentals: data structures, algorithms, and system design
• Proficiency in Python and/or TypeScript
• Experience building or consuming REST or GraphQL APIs
• Familiarity with relational databases and SQL
• Ability to work independently, take ownership of tasks, and communicate progress clearly
• Curiosity about scientific data or AI-driven software systems and a willingness to learn quickly

Bonus Points For

Data Platform Track

• Familiarity with NLP, document understanding (OCR, table/figure extraction), or multimodal models
• Experience with LLM applications, embeddings, or retrieval systems (chunking, reranking, vector search)
• Experience building evaluation sets, annotation workflows, or working with messy real-world data
• Interest in scientific document parsing or knowledge graph construction

Agentic SSR Track

• Experience with server-side rendering frameworks (Next.js, Remix, or similar)
• Exposure to LLM APIs, agentic frameworks (LangChain, LangGraph, or similar), or AI-assisted developer tooling
• Experience with cloud infrastructure (AWS, GCP, or Azure) or containerized environments (Docker, Kubernetes)
• Familiarity with event-driven architectures or message queues (Kafka, Pub/Sub, SQS)

Both Tracks

• Experience contributing to or maintaining open-source projects
• Prior internship or co-op experience in a software engineering role