01Key Responsibilities
AI Agent Configuration:
Lead the design, build, and testing of AI agents powered by large language models (LLMs), leveraging prompt engineering, tool use, reasoning workflows, and retrieval-augmented generation (RAG).
Convert business needs into requirements, designs, workflow logic, system interactions, and implementation plans.
Create and maintain specifications for agent behavior, workflow orchestration, tool interactions, exception handling, and human-in-the-loop paths to support reliable implementation and deployment.
Coordinate integration of AI agents with enterprise platforms, APIs, and data sources, building the connectivity, retrieval patterns, and workflow components needed to enable secure, connected, end-to-end business execution.
Establish evaluation, testing, and monitoring practices for AI outputs, including quality checks, failure handling, tuning, and issue triage to improve safety, reliability, and performance in production.
Productionize AI agents by supporting deployment, validation, release readiness, post-production monitoring, and ongoing optimization in partnership with platform and engineering teams.
Cross-Functional Collaboration & Leadership:
Partner with Product, Technology, business stakeholders, and delivery teams to define priorities, dependencies, and acceptance criteria, and drive effective delivery of AI solutions into target workflows.
Collaborate with Security, Legal, and Compliance partners to ensure implementations align with user and operational needs while incorporating required controls, privacy standards, and responsible AI practices.
Drive strong execution standards through disciplined implementation practices, code quality, testing rigor, and clear documentation across delivered solutions.
Communicate decisions, implementation trade-offs, delivery risks, and production readiness clearly to both technical and non-technical stakeholders.
This is a senior individual contributor role requiring strong ownership, cross-functional collaboration, and the ability to deliver complex AI solutions with limited oversight.
Governance, Reliability & Responsible AI:
Embed responsible AI principles and sound controls into solution design, including guardrails, fallback mechanisms, and audit-ready logging.
Help ensure AI solutions align with enterprise governance, security, and acceptable-use standards, including appropriate human oversight for sensitive us .
