Senior Staff Software Engineer, Agentic Search

Ironclad
San Francisco
Workplace: HybridFull timeUSD 220,000 - 270,000 annuallyFunction: Software EngineeringExperience: 10+ yearsSkills: ["Ownership","Technical leadership","Mentoring","Autonomy","Outcome-driven"]

Own the architecture for agentic search that combines LLMs with retrieval systems to answer complex, ambiguous questions about customers’ contracts. Drive eval-driven development by designing benchmarks and experiments, turning feedback into measurable improvements. Lead content understanding and ingestion pipelines so raw documents become retrieval-ready data, while setting technical direction for engineers across Ironclad’s AI organization.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Ironclad
Ironclad
2 days ago

Senior Staff Software Engineer, Agentic Search

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 4 hours agoStatus: Live

Job Summary

Own the architecture for agentic search that combines LLMs with retrieval systems to answer complex, ambiguous questions about customers’ contracts. Drive eval-driven development by designing benchmarks and experiments, turning feedback into measurable improvements. Lead content understanding and ingestion pipelines so raw documents become retrieval-ready data, while setting technical direction for engineers across Ironclad’s AI organization.
Location: San Francisco
Workplace: Hybrid
Employment Type: Full time
Job Function: Software Engineering
Seniority: Mid level

Key Responsibilities

  • •Own and evolve agentic search architecture that combines LLMs with retrieval for optimal answers to complex or ambiguous questions.
  • •Design and run benchmarks and experiments to measure search quality, using results to continuously improve the system.
  • •Raise the company’s overall search quality standard by contributing to and influencing the search quality bar.
  • •Own content understanding and ingestion by building NLP/LLM models and pipelines that convert raw documents into retrieval-consumable data.
  • •Set technical direction by defining architectural decisions that other engineers across the AI organization build on.

Pay and Benefits

Salary: USD 220,000 - 270,000 annually
Equity and Bonus:Equity
Perks:Health InsuranceDentalVisionParental LeavePaid Leave401k

Key Requirements

  • •10+ years building production systems with significant experience in search, information retrieval, content understanding, or recommendation systems at meaningful scale.
  • •Deep expertise in learned/hybrid retrieval, query understanding/NLU pipelines, or production LLM agent systems (ideally multiple).
  • •Production experience with search frameworks such as Elasticsearch (or Solr, Vespa, OpenSearch) and embedding search, including relevance tuning and reranking.
  • •Fluency with modern LLM APIs and multi-provider orchestration (Anthropic, OpenAI, Google), including token budgets and provider-specific tool-calling semantics.
  • •Experience building eval-driven workflows (offline benchmarks, regression detection, structured A/B comparisons) and demonstrating autonomy and technical leadership.
Experience:10+ yearsAILLMSearchInformation retrievalRecommendation systems
Skills:OwnershipTechnical leadershipMentoringAutonomyOutcome-driven
Tech Stack:LLMsRetrieval systemsNLPElasticsearchSolrVespaOpenSearchEmbedding searchLLM APIsMulti-provider orchestrationAnthropicOpenAIGoogleToken budgetsPrompt-cachingSFTRLRAGGoogle DocsPDFs

Company Brief

Ironclad
Provides a contract lifecycle management platform that automates contract creation, negotiation, approval, and analytics for legal and business teams. Integrates with enterprise systems to streamline contracting workflows and reduce legal bottlenecks.
Industry: LegalTech
Company Size: Large (251 to 1,000 employees)
Growth: Scaleup
Valuation: Unicorn (USD 1B+)
Funding: Series E+
Headquarters: San Francisco, United States
Founded: 2014
WebsiteLinkedIn