Senior Agentic (AI) Engineer

Job Description

Job Description: Senior Agentic AI Engineer

Job Title: Senior Agentic AI Engineer

Company Information

Company: Worth AI

Location: Miami, FL (Remote option available)

Work Model: Remote / Hybrid (Note: All remote hires must travel to Orlando, Florida at least twice per year for Town Halls and orientation).

Job Description

Worth AI is hiring a Senior Agentic AI Engineer to design and ship production agent systems that automate KYB, underwriting, and risk decisions on regulated financial data. You will own agents' end-to-end architecture, retrieval, tools, evals, and production deployment, partnering closely with the Chief AI Officer, applied scientists, and platform teams.

Key Responsibilities

• Design and ship multi-step agentic systems (planner/executor, tool-using, multi-agent, human-in-the-loop) for onboarding, underwriting, case review, and continuous monitoring.
• Architect agent graphs in LangGraph (or comparable frameworks like CrewAI, AutoGen, Claude Agent SDK) with explicit state, durable execution, retries, and safe fallbacks.
• Build the retrieval layer powering agents, including chunking, hybrid search, reranking, and grounded citation.
• Own the evaluation stack: golden sets, offline regression suites, LLM-as-judge, online A/B and shadow evals, and red-teaming for jailbreaks, prompt injection, and PII leakage.
• Expose agents to production systems via well-typed tools and MCP servers; treat tool surface area as a product.
• Drive production MLOps: deployment, versioning, traffic shaping, cost/latency budgets, tracing, and on-call playbooks for agent incidents.
• Partner with security and compliance to ensure agents operate within SOC 2, GDPR, CCPA, and fair-lending postures, ensuring auditability and explainability are built-in.
• Mentor engineers on agent patterns, prompt hygiene, eval discipline, and LLM failure modes.
  
  

Technology Stack

• Languages: Python, Node.js, TypeScript
• Agent/LLM Frameworks: LangGraph, LangChain, Claude Agent SDK, MCP, OpenAI SDK
• Models: Anthropic Claude, OpenAI, open-weight models
• Retrieval & Data: PostgreSQL, pgvector, OpenSearch, Kafka, Redshift, Redis
• Infrastructure: AWS, Kubernetes (EKS), ArgoCD, Terraform
• Evals & Observability: LangSmith, Langfuse, Braintrust-style tooling, DataDog
  
  

Requirements

• 5 years of software engineering experience, with 2 years building production LLM or agentic systems (excluding notebooks or demos).
• Hands-on experience with modern agent frameworks; LangGraph strongly preferred. Proven track record of shipping agents that run, fail gracefully, and recover.
• Strong RAG fundamentals: chunking, embeddings, hybrid retrieval, reranking, grounding, and the judgment to know when RAG is not the right answer.
• Real evaluative experience: utilizing golden sets and offline/online evaluations to make ship/no-ship decisions.
• Production MLOps fluency: experience deploying LLM workloads under real latency, cost, and reliability constraints.
• Strong Python skills; comfortable with TypeScript/Node.js.
• Solid systems engineering instincts: APIs, async patterns, queues, databases, and distributed system failure modes.
• Strong communication skills; ability to thrive in ambiguous, fast-moving environments.
• 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 Infrastructure as Code (IaC) with Terraform.
  
  

Success Metrics

• Agent Quality: Improvements in task success rate, grounding accuracy, and hallucination reduction.
• Production Reliability: Meeting SLOs for latency (P90/P99), tool-call success, and cost per task.
• Velocity: Rapid transition from prototype to production while maintaining evals and guardrails.
• Risk Posture: Zero material incidents related to prompt injection, PII leakage, or unsafe tool use.
• Force Multiplier: Creation of patterns, tools, and scaffolding adopted by the wider engineering team.
  
  

Benefits

• Health Care Plan (Medical, Dental & Vision)
• Retirement Plan (401k, IRA)
• Life Insurance
• Flexible Paid Time Off
• 9 Paid Holidays
• Family Leave
• Remote/Hybrid options (with Orlando-based specific perks: Free Food & Snacks, Wellness Resources)