AI Engineer, Search & Knowledge Systems

About the role

We are looking for an AI Engineer specializing in search, retrieval, knowledge systems, and relationship discovery. You will design and build the systems that help Pi understand and connect security-relevant context across code, pull requests, tickets, documents, incidents, findings, cloud resources, and customer environments. Your work will power the retrieval, grounding, provenance, and relationship modeling behind Pi’s agentic security workflows.

Responsibilities

• Build AI-powered search and discovery systems across structured and unstructured security and engineering data.
• Develop retrieval-augmented generation pipelines using embeddings, hybrid search, reranking, chunking, metadata filtering, grounding, and citation-aware generation.
• Build knowledge systems that represent entities, relationships, events, decisions, vulnerabilities, controls, code ownership, services, and provenance.
• Improve relevance, recall, precision, ranking quality, and answer accuracy across search, investigation, and agentic workflows.
• Design systems for entity extraction, entity resolution, ontology design, relationship inference, and semantic enrichment.
• Evaluate and combine lexical search, semantic search, hybrid search, graph-based retrieval, and agentic retrieval patterns.
• Build evaluation frameworks for retrieval quality, hallucination reduction, grounding, freshness, citation accuracy, and user satisfaction.
• Build ingestion and indexing pipelines that normalize, enrich, connect, and refresh data from multiple customer and product sources.
• Monitor production AI systems, debug retrieval failures, improve latency, and optimize cost/performance tradeoffs.
• Partner with product, backend, frontend, platform, and security teams to turn ambiguous customer needs into reliable knowledge systems.
• Help create the foundation that lets Pi preserve institutional security memory and prevent recurring vulnerability classes.

Requirements

• Strong software engineering experience in Python, TypeScript, or similar languages.
• Experience building production search, recommendation, knowledge management, or AI retrieval systems.
• Hands-on experience with RAG architectures, embedding models, vector search, rerankers, and LLM-backed workflows.
• Strong understanding of information retrieval concepts such as indexing, ranking, query expansion, relevance scoring, recall/precision, BM25, dense retrieval, and hybrid search.
• Experience working with structured and unstructured data, including code, documents, tickets, logs, metadata, databases, APIs, and event streams.
• Experience designing evaluation methods for search relevance, retrieval quality, and AI-generated answers.
• Ability to build reliable, observable, production-grade systems.
• Strong product judgment: you can translate ambiguous user needs into practical search, knowledge, and retrieval systems.
• Strong security instincts around authorization, tenant isolation, data exposure, provenance, and safe handling of customer context.
• Ability to work in a fast-moving startup environment with ownership, autonomy, and good judgment.

Qualifications

• Nice to have: experience with knowledge graphs, graph databases, graph embeddings, ontology design, or taxonomy management.
• Nice to have: experience with entity linking, entity resolution, relationship extraction, or semantic enrichment.
• Nice to have: experience with LLM orchestration, agentic search, tool use, or multi-step reasoning systems.
• Nice to have: experience with NLP techniques such as named entity recognition, classification, summarization, clustering, topic modeling, or semantic similarity.
• Nice to have: experience with data pipelines for ingesting, transforming, indexing, and refreshing large datasets.
• Nice to have: experience with cloud platforms and production AI infrastructure.
• Nice to have: experience with security products, developer tools, code analysis, cloud security, enterprise search, legal tech, finance, healthcare, or research platforms.