Senior AI Systems Engineer — Enterprise Search & LLMs

ironcladhq; San Francisco (CA); Hybrid; USD 180,000 - 200,000; Full time

Benefits offered by this job

Health coverage and benefits

Parental leave

Maven family forming support

Paid time off

Wellbeing stipends

Mental health support

Pre-tax commuter benefits

401(k) with employer match

Team events

Job summary

Ironclad in San Francisco is hiring for an Intelligence Platform Engineer focused on agentic search, retrieval, and content understanding at scale. You will build scalable systems that blend LLMs with retrieval, design eval-driven benchmarks, and push the quality bar for search and content understanding.

The role requires 4+ years building production systems in search or related areas, with hands-on experience across retrieval, LLM APIs, and multi-provider orchestration.

Qualifications

• 4 years experience building production systems, with hands-on experience in search, information retrieval, content understanding or recommendation systems at meaningful scale.
• Expertise in one of: learned/hybrid retrieval (lexical + vector + reranking), query understanding/NLU pipelines, or production LLM agent systems — ideally more than one.
• Experience with search frameworks (Elasticsearch or equivalent — Solr, Vespa, OpenSearch; embedding search) in production, including relevance tuning and reranking.
• 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.
• Experience building eval-driven workflow — offline benchmarks, regression detection, structured A/B comparison — as opposed to shipping and hoping.
• Strong ownership and communication.
• Care deeply about system scalability, reliability, and right design patterns.
• Comfortable operating in a dynamic, fast-paced and outcome-driven environment.

Responsibilities

• Agentic search systems: Evolve the architecture that combines LLM and retrieval system to produce optimal answer for complex or ambiguous questions.
• Eval-driven development: Design and run the benchmarks and experiments that measure search quality, and use that feedback to improve the system.
• Search quality: Contribute to the company's search quality bar.
• Content understanding & ingestion: turn raw documents into processed data that can be consumed by retrieval systems, by building/using NLP/LLM models and pipelines.

Skills

search

information retrieval

content understanding

recommendation systems

LLM APIs

multi-provider orchestration

ownership

communication

system scalability

Tools

Elasticsearch

Solr

Vespa

OpenSearch

Embedding search

Anthropic

OpenAI

Google

Job description

Ironclad in San Francisco is hiring for an Intelligence Platform Engineer focused on agentic search, retrieval, and content understanding at scale. You will build scalable systems that blend LLMs with retrieval, design eval-driven benchmarks, and push the quality bar for search and content understanding.

The role requires 4+ years building production systems in search or related areas, with hands-on experience across retrieval, LLM APIs, and multi-provider orchestration.