Senior AI Agent Engineer
Confirmed on the employer's own hiring board on Oct 31, 2026. First seen by Alion on Oct 28, 2026.
About us
Relay is a cross-chain payments protocol that provides instant, low-cost cross-chain bridging, swaps, and transactions. We're the fastest and cheapest way to bridge and transact across chains, serving over 5 million users who have completed 59+ million transactions with $6+ billion in volume across 85+ chains.
Our company mission is to make transacting across chains as fast, cheap, and reliable as online payments. We are building the core infrastructure to abstract chains from end user payments, enabling the next billion users to experience the benefits of blockchain without the UX burdens.
About the role
We're hiring a Senior AI Agent Engineer on the Developer Experience team. You'll own Relay's internal AI agent - a Slack-native agent that works across our tools to investigate issues, answer questions, and complete operational work.
This is a hands-on builder role. You're measured by what the agent gets done, accurately and safely.
What you'll do
Cover US business hours
This role is remote within the United States, with dependable overlap with the teams whose workflows you're automating.
Own and improve the agent
Own the agent backlog; prioritize by impact, frequency, and risk
Review real misses each week and turn them into regression evals, fixed tools, or better guidance
Turn expert workflows into agent skills, decision logic, and escalation paths
Build knowledge systems that help agents find, connect, and reason over Relay's structured and unstructured information, with clear provenance and freshness
Improve retrieval, orchestration, and verification; own regressions through resolution
Measure task success, correction rate, latency, and cost, and report them
Connect agents to Relay's systems safely
Integrate agents with internal systems through APIs and MCP tools
Choose deterministic code, simple automation, or agent behavior on the merits
Treat permissions, side effects, human approval, and failure recovery as product features
About you
You're a product-minded engineer who ships AI systems into real workflows
You care about correctness, permissions, and failure handling as much as model capability
You read traces before you change prompts
You'd often rather add a linter, a type, or a test than tune a prompt
You know when conventional software beats an agent
You can sit with a domain expert, extract how they decide, and encode it into testable behavior
You're comfortable being the first dedicated hire for a new function
Skills and abilities
Must-have
5+ years in software engineering, developer tooling, or platform engineering
Production experience with LLM agents: tool use, retrieval, structured outputs, orchestration
Experience building search, retrieval, or knowledge systems across structured and unstructured information
Strong TypeScript or Python and experience building API integrations
Experience designing evals or automated tests for nondeterministic software
Familiarity with permissions, secrets, auditability, and safe handling of side effects
Strong written communication; you can turn an expert's workflow into a precise spec
Nice to have
Experience with MCP or comparable tool and context protocols
Experience with Slack apps, support automation, or internal platforms
Experience with entity resolution, knowledge graphs, ontology or taxonomy design, ranking, or semantic enrichment
Experience in crypto, payments, or another high-stakes domain
What we offer
Competitive base salary
Equity package
Comprehensive health benefits
Unlimited PTO policy with encouraged minimum
Remote-first culture with emphasis on collaboration, communication, and flexibility