Staff/Senior Staff Software Engineer (Agentic Search)

Join Ironclad's Intelligence Platform team as a Staff/Senior Staff Software Engineer (Agentic Search). In this role, you will own the architecture that combines LLMs and retrieval systems to answer complex questions about contracts. You will drive eval-driven development, raise the search quality bar, and own content understanding and ingestion. You will also set the technical direction for other engineers across the AI organization.

• Architect and evolve the systems that combine LLMs and retrieval to produce optimal answers to complex or ambiguous questions.
• Design and run the benchmarks and experiments that measure search quality, and use that feedback to continuously improve the system.
• Define architectural decisions and technical direction that other engineers across the AI organization build on.

• Fluency with modern LLM APIs and multi-provider orchestration (Anthropic, OpenAI, Google) — reasoning about token budgets, provider-specific tool-calling semantics, and prompt-caching trade-offs
• Demonstrated depth in one of: learned/hybrid retrieval (lexical + vector + reranking), query understanding/NLU pipelines, or production LLM agent systems — ideally more than one
• 10+ years building production systems, with a substantial portion in search, information retrieval, content understanding, or recommendation systems at meaningful scale
• Experience with search frameworks (Elasticsearch or equivalent — Solr, Vespa, OpenSearch; embedding search) in production, including relevance tuning and reranking
• Comfortable operating in a dynamic, fast-paced, outcome-driven environment
• Strong autonomy, ownership, and technical leadership across teams, including mentoring senior engineers and driving architectural decisions
• Experience building eval-driven workflows — offline benchmarks, regression detection, structured A/B comparison — as opposed to shipping and hoping
• Hands-on experience with post-training algorithms and infrastructure, including SFT and RL
• Experience with content understanding and/or information retrieval in structured-document-heavy domains
• Prior work on RAG systems involving data sources in different formats (Google Docs, PDFs, DOCX, etc.)