Senior/Staff Software Engineer (Search & Retrieval)

About Actively AI Actively AI is defining a new category: Intelligence-Led Revenue. Revenue organizations have always been bottlenecked on human capacity. Reps triage which accounts get attention. Context disappears at every handoff. On any given day, the vast majority of accounts have exactly zero people thinking about them. Actively addresses this at the structural level. Our platform deploys Per-Account AgentsTM across our customers’ TAM, working 24/7 to research, identify opportunities, and advance next steps without being asked. Leading enterprises including Ramp, Ironclad, and Samsara are already making this shift. Our co-founders are former Stanford AI researchers, and the team comes from Harvard, CMU, Berkeley, Brex, Scale AI, and Google. We've raised $68M from TCV, First Harmonic, Bain Capital Ventures, First Round Capital, and more. About the Role We’re looking for a Senior / Staff Software Engineer - Search & Retrieval to build and scale the systems that power Actively’s AI agents to find, rank, and reason over data. When an Actively agent decides which account to prioritize or what action to take next, it reasons over retrieved context; data pulled from customer records, call transcripts, signals, and internal intelligence. Get that retrieval right and the agent acts with precision. Get it wrong and it doesn't matter how good the underlying model is. You'll design and build the search, retrieval, and relevance infrastructure that feeds every agent at Actively from the enrichment and entity extraction that turns raw data into something queryable, to the ranking systems that determine what context an agent actually sees. The data is diverse, messy, and customer-specific. Freshness matters. So does precision. And the consumer isn't a human browsing results but it's a model that will act on whatever you give it. What You’ll Do Build the retrieval layer agents depend on. Design and scale the search and retrieval infrastructure that feeds Actively's agents, covering indexing, querying, ranking, and filtering across diverse customer data sources. Turn raw, unstructured data into something retrievable. Design enrichment and entity extraction systems that pull structure, relationships, and context out of call transcripts, documents, and signals, making them queryable in ways that improve what agents actually see. Own the Search for Agents Architecture: Define how data gets represented and stored, making deliberate choices about granularity, embedding models, and index configuration for different data types and use cases. Build and iterate on ranking systems. Design and deploy reranking layers that maximize relevance for agent queries, and evolve them as data patterns and use cases change. Develop shared retrieval primitives. Build the APIs and retrieval interfaces used by the Intelligence, Assistant, and Orchestration teams, balancing flexibility with consistency across consumers. Own retrieval quality end to end. Build and maintain evaluation infrastructure using classical IR metrics, task-level success signals, and LLM-based techniques, catching regressions before they affect agent behavior. Who You Are Deep experience in search or retrieval systems. You have 5+ years building and operating retrieval systems in production, across multiple customers, data sources, or domains, and understand what relevance actually means at scale. Background in information retrieval or applied ML. You've tuned relevance, deployed reranking strategies, and improved result quality in production, not just in experiments. Understands the freshness problem. You've built retrieval pipelines over fast-changing data, including near-real-time indexing, incremental updates, or event-driven ingestion, and know how freshness trade-offs affect system design. Comfortable with hybrid retrieval approaches. You've worked with systems that combine semantic search, keyword and lexical matching, and metadata filtering to balance recall, precision, and reliabil