Worth AI

Worth AI

Senior Agentic (AI) Engineer

Orlando, Florida, United States · Senior

Sponsorship not specifiedDetected 68 days ago
TypeScriptPythonNode.jsDistributed SystemsPostgreSQLRedisElasticsearchRedshiftAWSKubernetesTerraformDatadogKafkaMachine LearningLLMsRAGAgentic AILLMOpsMLOpsLangGraphComplianceSystems EngineeringCollaborationUnderwriting

About the role

  • Architect agent graphs in LangGraph (or comparable - CrewAI, AutoGen, Claude Agent SDK) with explicit state, durable execution, retries, and safe fallbacks.
  • Mentor engineers on agent patterns, prompt hygiene, eval discipline, and LLM failure modes.

Responsibilities

  • Partner with security and compliance to keep agents inside SOC 2, GDPR, CCPA, and fair-lending posture - auditability and explainability built in, not bolted on.
  • Agents you own meet defined SLOs for latency (P90/P99), tool-call success, and cost per task.
  • Zero material incidents tied to prompt injection, PII leakage, or unsafe tool use on agents you own.
  • Patterns, tools, and eval scaffolding you build get adopted across engineering.

Nice to have

  • LangSmith / Langfuse / Braintrust-style tooling, DataDog
  • Hands-on experience with a modern agent framework (LangGraph strongly preferred) and a track record of shipping agents that run, fail gracefully, and recover.
  • Real eval experience golden sets, offline and online evaluations, used to make ship/no-ship calls.

Skills

  • Expose agents to production systems via well-typed tools and MCP servers.
  • Treat tool surface area as a product.
  • deployed LLM workloads under real latency, cost, and reliability constraints.
  • Strong Python; comfortable in TypeScript / Node.js.
  • Solid systems engineering instincts APIs, async patterns, queues, databases, distributed system failure modes.
  • Calibrated communicator; thrives in ambiguous, fast-moving environments.
  • Prior experience in fintech, lending, payments, KYB/KYC, fraud, or AML.

This listing is sourced directly from Worth AI's careers page and normalized into a canonical job model.