Anrok
Software Engineer, Agentic AI Infrastructure
San Francisco +2 · Hybrid · Full-time · Posted Jun 8, 2026
- Location
- San Francisco
Salt Lake City
New York City - Experience
- 3+ years building and operating distributed, production-grade systems.
About the job
Build foundational distributed infrastructure that enables Anrok’s AI agents to reason over tax data and reliably execute compliance workflows at scale.
What you'll do
- Design and ship fault-tolerant agent infrastructure for memory, state management, and execution.
- Own agent-service architecture and build evaluation, observability, and reliability tooling through production deployment and iteration.
- Collaborate on compliance-focused agent primitives, improve system performance and operational health, and mentor engineers.
What they ask for
- 3+ years building and operating distributed, production-grade systems.
- Experience designing scalable, resilient, fault-tolerant services and deploying AI agents or LLM-powered systems in production.
- Experience across the software development lifecycle, including design, code review, testing, deployment, and on-call ownership.
- Familiarity with prompt engineering, eval frameworks, RAG pipelines, tool calling, and agent orchestration.
Tools
LLM, RAG
AI focus
Build the infrastructure for AI agents to reason about tax data and act across jurisdictions, including agent memory, state management, execution, evaluation, observability, and reliability.
Model-written summary · the original posting is authoritative