AI Engineer - LLM Development & Agentic AI

Role Summary

We are seeking an AI Engineer II to design and deliver responsible, secure AI-powered tools that improve onboarding (“boarding”) and operational execution. This role focuses on implementing agentic AI patterns (multi-step workflows, tool-use, and human-in-the-loop approvals) and integrating them into production systems to reduce manual effort, increase consistency, and improve service outcomes.

Key Responsibilities

• Build and enhance AI-assisted operational tools such as guided intake, knowledge-grounded Q&A, case/ticket summarization, and runbook execution support.
• Implement agentic workflows with clear guardrails: input validation, policy-aware prompting, approval steps, fallbacks, and safe failure modes.
• Integrate AI capabilities with internal services and data sources through approved APIs; collaborate with platform teams to onboard integrations.
• Develop retrieval and grounding approaches (e.g., RAG) to ensure responses are based on approved knowledge sources with proper access controls.
• Create and maintain automated evaluations (quality, groundedness, safety), plus telemetry for monitoring performance, cost, and reliability.
• Contribute to code reviews, unit/integration tests, CI/CD, and operational readiness (documentation, alerts, runbooks).
• Partner with operations SMEs, product owners, risk, and security to refine requirements and ensure compliant delivery.

Required Qualifications

• Bachelor’s degree in Computer Science, Engineering, or equivalent practical experience.
• 2+ years of software engineering experience building production services or applications.
• Demonstrated experience implementing LLM-powered features (prompting, tool/function calling, RAG, agent/workflow orchestration).
• Proficiency in at least one of: Python, Java, or TypeScript; ability to work with REST APIs and event-driven patterns.
• Strong engineering fundamentals: data structures, debugging, testing, and secure coding practices.
• Experience handling sensitive data responsibly and applying least-privilege access and secure SDLC practices.

Preferred Qualifications

• Experience supporting operational workflows (service management, onboarding operations, incident/change processes).
• Familiarity with search/retrieval systems, ranking, and content chunking/embedding strategies.
• Experience with observability (logs/metrics/traces) and operational support for production services.
• Knowledge of Responsible AI practices (privacy, bias, safety, transparency) and implementing human-in-the-loop controls.
• Experience working in regulated environments (financial services a plus).

What Success Looks Like

• Delivers 1–2 production-ready AI capabilities that measurably improve cycle time, quality, or operational throughput.
• Establishes baseline evaluations and monitoring to prevent regressions and ensure safe operation.
• Produces clear documentation and supports smooth handoff/operations readiness.

Compliance & Responsible AI Expectations

• Adheres to Client Responsible AI Guidelines and AI usage compliance requirements.
• Ensures appropriate handling of sensitive data (PII, client data, credentials) with auditability and access controls.
• Uses only approved AI platforms and integration patterns; evaluates emerging interoperability standards only when permitted by policy.