Al Developer / Agentic Al Engineer

We are building an agentic Al platform to transform commercial banking customer service. The Al developer will design, build, and operate LLM-powered agents that interpret inbound servicing requests (e.g., email / case intake), retrieve grounded knowledge, and execute approved workflows through secure too/API integrations - with enterprise-grade controls, observability, and human-in-the-loop patterns.
 

This role sits within a cross-functional team with Product, Operations, Technology, and Risk partners and focuses on delivering production-ready agentic Al capabilities for regulated financial services Responsibilities
 

Agentic Al Solution Development
 

• Build and enhance LLM/agent orchestration (Planner/supervisor patterns, tool-using agents, routing, guardrails).
   
• Implement intent classification information extraction validation and decision logic for servicing workflows
   
• Developed tool calling integrations to downstream systems (CRM, workflow engine, core banking services, case management)
   
• Implement human-in-the-loop workflows (review, approval, escalation, override) based on confidence/risk thresholds
   

Knowledge and grounding (RAG)
 

• Design and implement retrieval-augmented generation (RAG) for policy procedure grounding and resolution guidance
   
• Build knowledge ingestion pipelines with refresh/versioning
   
• Improve answer quality via chunking strategies, embeddings re ranking and context management
   

Quality, Safety and Evaluation
 

• Define and run evaluation frameworks: golden datasets, scenario tests, regression tests, and automated scoring.
   
• Reduce hallucinations and risk by implementing prompt policies, constraints, structured outputs, and verification steps.
   
• Partner with risk slash compliance to ensure traceability, audit logs, explain ability requirements are met.
   

Production Readiness and Operations
 

• Implement observability for agents (latency, cost, tool failures, drift, quality signals, escalation rates).
   
• Support CI/CD for agent prompts and configurations (versioning, approvals, rollback).
   
• Collaborate with platform and security teams on secrets management, access controls, PIl protections, and safe deployments.
   

Required Qualifications
 

• 4+ years of software engineering experience or equivalent with strong CS fundamentals
   
• Hands-on experience building with LLMs and modern Al app stack (agents, RAG, tool/function calling).
   
• Strong proficiency in Python and building back-end services/APls.
   
• Experience with at least one: LangChain/ LangGraph, Llamalndex, Semantic Kernel or equivalent frameworks.
   
• Experience with vector databases and search (e.g., Pinecone, Weaviate, Milvus, OpenSearch/Elastic, )
   
• Experience deploying services in cloud environments (AWS/Azure/GP) with basic DevOps practices
   
• Strong understanding of security and privacy principles (PIl handling, least privilege, audit logging)
   
• Preferred Qualifications
   
• Experience in financial services or other regulated domains (risk controls, compliance audit readiness)
   
• Experience integrating with enterprise workflows (e.g., ServiceNow, Custom workflow engines,
  BPM/RPA)
• Familiarity with model evaluation approaches (LLM-as-judge, rubric scoring, retrieval evals, offline/online testing)
   
• Experience with messaging/eventing (Kafka/SQS), email ingestion pipelines, and document processing
   
• Exposure to MRM concerns and governance (model cards, risk assessments, validation processes)