Staff/Principal Engineer, Search & Retrieval

Lila Sciences • San Francisco, CA

3d

About The Position

Lila Sciences is hiring a Staff/Principal Engineer, Search & Retrieval (Enterprise AI) to own the platform through which scientists and agents access scientific knowledge, including published literature and patents, customer-supplied documents, lab protocols, and structured experimental records. The role will build retrieval-augmented generation over unstructured text and a scientific knowledge graph linking literature to structured experimental records. The platform must support scientific workloads across enterprise customers, with tenancy enforced in the index and graph rather than only at the application layer. The engineer will own the stack end to end, from ingestion and retrieval through cited answers that scientists can trace to their evidence.

This is a deeply technical senior individual-contributor role with high autonomy, direct ownership of critical platform systems, and broad architectural influence. The engineer will help define the shared retrieval foundation used across scientific workloads, build graph retrieval and its fusion with vector and lexical search, develop agentic search and an autonomous research loop, own retrieval quality and its evaluation harness, and build ingestion and extraction pipelines for diverse scientific data. The role involves working across platform engineering, infrastructure, AI/ML, and scientific teams in a fast-moving environment.

Requirements

• At least 8 years of software development experience.
• Production ownership of a search, retrieval, RAG, or knowledge graph system depended on by real users.
• Production experience building semantic search, including embedding models, vector indexes such as HNSW or IVF, hybrid lexical and vector retrieval, and reranking.
• Experience in high-growth environments where speed-to-value mattered alongside long-term architecture.
• Ability to explain how retrieval quality was measured, including recall, groundedness, and citation accuracy, and how regressions were caught.
• Hands-on coding experience in Python and modern backend frameworks such as FastAPI and async Python.
• Experience with modern cloud-native architectures, including Kubernetes, Terraform, and AWS.
• Strong cross-functional communication and ability to influence architecture across teams.
• BS, MS, or Ph.D. in Computer Science or a related field of study, or equivalent experience.

Nice To Haves

• Graph database experience.
• Experience shipping RAG or semantic search in a regulated or enterprise context and navigating security and compliance review under regimes such as SOC 2, HIPAA, GxP (including ALCOA+ data integrity), or FedRAMP.
• Experience with permission-aware retrieval over access-controlled data.
• Experience with document understanding at scale, including OCR, layout-aware parsing, and table and figure extraction from scientific literature.
• Experience with agentic retrieval and GraphRAG patterns, including how to evaluate them.
• Experience with platforms serving scientific or laboratory data, such as LIMS, ELN, bioinformatics, or materials informatics, and understanding of provenance and traceability requirements.
• Experience with domain-specific corpora and scientific ontologies such as UMLS, MeSH, ChEBI, GO, UniProt, or Materials Project, where specialized vocabulary affects general-purpose embeddings and entity linking.
• Experience with knowledge graph construction and graph retrieval using property graph or RDF stores.

Responsibilities

• Provide technical leadership across platform engineering, infrastructure, AI/ML, and scientific teams.
• Define the shared retrieval foundation and architecture for scientific workloads across the company.
• Build a scientific knowledge graph from literature and structured experimental records.
• Own graph retrieval and combine it with vector and lexical search to deliver cited answers.
• Build the autonomous research loop, from query planning through retrieval to traceable reasoning.
• Own the end-to-end retrieval pipeline and its evaluation harness, including retrieval quality and regression detection.
• Build ingestion and extraction pipelines that transform scientific data, including PDFs, patents, and lab protocols, into semantically searchable evidence.
• Own the retrieval stack end to end, from ingestion through retrieval to evidence-traceable answers.

Benefits

• Competitive base compensation with bonus potential and generous early-stage equity.
• U.S. full-time employees receive medical, dental, and vision coverage.
• Employer-paid life and disability insurance for U.S. full-time employees.
• Flexible time off and generous company-wide holidays for U.S. full-time employees.
• Paid parental leave for U.S. full-time employees.
• Educational assistance program for U.S. full-time employees.
• Commuter benefits, including bike share memberships for office-based employees.
• Company-subsidized lunch program.
• Comprehensive benefits program tailored to the employee's region for full-time employees outside the U.S.

What This Job Offers

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