Senior Agentic AI Engineer

Posted 24d ago

The employer’s full description could not be read from their board. This is a summary of the posting — follow the apply link for the original.

Design and ship multi-step agentic systems for onboarding, underwriting, case review, and monitoring
Architect agent graphs in LangGraph with explicit state, durable execution, retries, and fallbacks
Build retrieval layer: chunking, hybrid search, reranking, grounded citation
Own eval stack: golden sets, offline regression, LLM-as-judge, online A/B, red-teaming
Expose agents via well-typed tools and MCP servers
Drive production MLOps: deployment, versioning, traffic shaping, cost/latency budgets, tracing
Partner with security and compliance for SOC 2, GDPR, CCPA, fair-lending posture
Mentor engineers on agent patterns, prompt hygiene, eval discipline, LLM failure modes

5+ years software engineering, 2+ years production LLM or agentic systems
Hands-on experience with a modern agent framework (LangGraph strongly preferred)
Strong RAG fundamentals: chunking, embeddings, hybrid retrieval, reranking, grounding
Real eval experience with golden sets, offline and online evaluations
Production MLOps fluency for LLM workloads under latency, cost, reliability constraints
Strong Python; comfortable in TypeScript / Node.js
Solid systems engineering: APIs, async patterns, queues, databases, distributed failure modes

Prior experience in fintech, lending, payments, KYB/KYC, fraud, or AML
Experience building MCP servers or other structured tool interfaces for LLMs
Background in classical ML (ranking, scoring, calibration)
Experience designing explainable / auditable AI workflows for regulated environments
Open-source contributions to agent frameworks, eval tooling, or retrieval libraries
AWS depth (EKS, MSK, RDS, S3, Lambda) and IaC with Terraform

Skills