{"id":1405239,"url":"https://alion.io/job/pi-ai-engineer-search-knowledge-systems","title":"AI Engineer, Search & Knowledge Systems","company":{"id":1837564,"name":"Pi","domain":"pi.security","url":"https://alion.io/company/pi-security","size_band":"11-50","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":null,"employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["San Francisco, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":160000,"max_usd":350000,"period":"year","method":"role_country_seniority_unknown","sample_n":2986},"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Agentic Workflows","optional":false},{"name":"AI Agents","optional":false},{"name":"Embeddings","optional":false},{"name":"Hallucination","optional":false},{"name":"Hybrid Search","optional":false},{"name":"LLM","optional":false},{"name":"LLM Guardrails","optional":false},{"name":"RAG","optional":false},{"name":"Reranking","optional":false},{"name":"Semantic Search","optional":false},{"name":"Semantic Search","optional":false},{"name":"Docker","optional":true},{"name":"Function Calling","optional":true},{"name":"Knowledge Graph","optional":true},{"name":"NLP","optional":true},{"name":"PostgreSQL","optional":true},{"name":"Python","optional":true},{"name":"Tool Use","optional":true},{"name":"TypeScript","optional":true}],"status":"live","first_seen_at":"2026-07-08T16:08:22Z","employer_posted_date":"2026-07-08","last_verified_at":"2026-09-30T23:12:13Z","board_verified":true,"closed_at":null,"days_open":84,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":84},"description":"AI Engineer, Search & Knowledge Systems\nAbout Pi\nPi is building an agentic product security platform for teams that need to secure software at the speed they build it.\nModern development is accelerating, but security knowledge is still scattered across code, tickets, documents, incidents, reviews, and the people who remember why decisions were made. Pi turns that context into institutional security memory, helping teams triage faster, remediate in context, prevent repeat vulnerability classes, and embed security guardrails where engineering work already happens.\nWe are building for a future where security is not a blocker at the end of the development process. It is part of how software gets designed, reviewed, shipped, and improved.\nRead about Pi Security on Forbes!\nAbout The Role\nWe are looking for an AI Engineer specializing in search, retrieval, knowledge systems, and relationship discovery.\nYou 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.\nThis role is ideal for someone who combines strong software engineering with deep interest in information retrieval, applied AI, knowledge representation, ranking, evaluation, and production systems.\nWhat You’ll Do\nBuild AI-powered search and discovery systems across structured and unstructured security and engineering data.\n\nDevelop retrieval-augmented generation pipelines using embeddings, hybrid search, reranking, chunking, metadata filtering, grounding, and citation-aware generation.\n\nBuild knowledge systems that represent entities, relationships, events, decisions, vulnerabilities, controls, code ownership, services, and provenance.\n\nImprove relevance, recall, precision, ranking quality, and answer accuracy across search, investigation, and agentic workflows.\n\nDesign systems for entity extraction, entity resolution, ontology design, relationship inference, and semantic enrichment.\n\nEvaluate and combine lexical search, semantic search, hybrid search, graph-based retrieval, and agentic retrieval patterns.\n\nBuild evaluation frameworks for retrieval quality, hallucination reduction, grounding, freshness, citation accuracy, and user satisfaction.\n\nBuild ingestion and indexing pipelines that normalize, enrich, connect, and refresh data from multiple customer and product sources.\n\nMonitor production AI systems, debug retrieval failures, improve latency, and optimize cost/performance tradeoffs.\n\nPartner with product, backend, frontend, platform, and security teams to turn ambiguous customer needs into reliable knowledge systems.\n\nHelp create the foundation that lets Pi preserve institutional security memory and prevent recurring vulnerability classes.\n\nWhat We’re Looking For\nStrong software engineering experience.\n\nExperience building production search, recommendation, knowledge management, or AI retrieval systems.\n\nHands-on experience with RAG architectures, embedding models, vector search, rerankers, and LLM-backed workflows.\n\nStrong understanding of information retrieval concepts such as indexing, ranking, query expansion, relevance scoring, recall/precision, BM25, dense retrieval, and hybrid search.\n\nExperience building language-aware code indexing and code intelligence systems, including AST parsing, symbol and reference resolution, call graphs, control- and data-flow analysis, and compiler or Language Server Protocol (LSP) tooling.\n\nExperience working with structured and unstructured data, including code, documents, tickets, logs, metadata, databases, APIs, and event streams.\n\nExperience designing evaluation methods for search relevance, retrieval quality, and AI-generated answers.\n\nAbility to build reliable, observable, production-grade systems.\n\nStrong product judgment: you can translate ambiguous user needs into practical search, knowledge, and retrieval systems.\n\nStrong security instincts around authorization, tenant isolation, data exposure, provenance, and safe handling of customer context.\n\nAbility to work in a fast-moving startup environment with ownership, autonomy, and good judgment.\n\nTechnologies We Use\nPython\n\nTypeScript\n\nEmbedding models\n\nRerankers\n\nLexical, semantic, and hybrid search\n\nVector search\n\nPostgreSQL\n\nGraph-based data modeling\n\nWorkflow orchestration systems\n\nData ingestion and indexing pipelines\n\nEvaluation and observability tooling\n\nDocker\n\nNice To Have\nExperience with knowledge graphs, graph databases, graph embeddings, ontology design, or taxonomy management.\n\nExperience with entity linking, entity resolution, relationship extraction, or semantic enrichment.\n\nExperience with LLM orchestration, agentic search, tool use, or multi-step reasoning systems.\n\nExperience with NLP techniques such as named entity recognition, classification, summarization, clustering, topic modeling, or semantic similarity.\n\nConsistent history of delivering complex projects for a SaaS product.\n\nExperience in fast-paced high growth startups.\n\nConsistent history of spending multiple years in each role making a big impact.\n\nExperience with data pipelines for ingesting, transforming, indexing, and refreshing large datasets.\n\nExperience with cloud platforms and production AI infrastructure.\n\nExperience with security products, developer tools, code analysis, cloud security, enterprise search, legal tech, finance, healthcare, or research platforms.\n\nExample Projects\nBuild a hybrid search system that combines keyword search, semantic search, metadata filters, and graph traversal.\n\nDesign a knowledge system that connects repositories, services, pull requests, tickets, findings, vulnerabilities, cloud resources, owners, and decisions.\n\nBuild a RAG system that produces grounded answers with citations, confidence signals, and traceable source context.\n\nCreate pipelines for extracting entities and relationships from code, tickets, documents, security findings, logs, and cloud metadata.\n\nDevelop relevance evaluation datasets and automated tests for retrieval quality, grounding, and answer accuracy.\n\nImprove agentic workflows by giving AI systems better context, better retrieval, and better understanding of customer-specific security history.\n\nSuccess In This Role Looks Like\nUsers can find the right security and engineering context faster and with higher confidence.\n\nAI-generated answers are grounded, cited, and reliable.\n\nRelationships that were previously hidden across code, tickets, documents, findings, and infrastructure become discoverable and useful.\n\nSearch relevance, retrieval accuracy, grounding quality, and system latency measurably improve over time.\n\nKnowledge systems are maintainable, observable, and extensible as new data sources are added.\n\nThe product helps customers understand risk, act faster, and prevent the same security issues from recurring.","description_format":"text","description_chars":7008,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":[],"lifecycle":[{"event":"open","at":"2026-09-28T17:25:23Z"}],"liveness":{"score":16,"band":"cold","label":"Long shot","p_open":1,"p_active":0.261,"p_room":0.6,"age_days":84,"expected_fill_days":96,"reasons":["conf:6","win:late","crowd:"],"computed_at":"2026-10-01T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/pi-ai-engineer-search-knowledge-systems","json_url":"https://alion.io/job/pi-ai-engineer-search-knowledge-systems.json","meta":{"generated_at":"2026-10-01T11:00:31Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","usage":{"tier":"crawler","counted_by":"address","units_charged":1,"used_today":2288,"day_limit":5000,"remaining_today":2712,"minute_limit":60,"resets_at":"2026-10-02T00:00:00Z"}}}