<p>Description</p> <p>4 Days in the office from any of our locations in Johnston RI,Iselin NJ, Westwood or Medford MA, or Phoenix AZ and couple other locations</p> <p>Role is not relocation eligible.</p> <p>Senior AI Software Engineer (Agentic AI / AI Agents)</p> <p>About the Role</p> <p>We are seeking a hands-on, results-driven Senior AI Software Engineer to build and scale Agentic AI capabilities-AI systems that can plan, act, and complete tasks through tool use and workflow orchestration-across enterprise platforms. This role is pivotal in delivering secure, reliable, and compliant AI Agents that integrate into customer and colleague journeys, accelerate time-to-market, and improve operational efficiency.</p> <p>You will operate at the intersection of software engineering and applied AI, owning end-to-end delivery-from architecture and implementation to deployment, observability, and operational excellence.</p> <p>Key Responsibilities</p> <p>Build and Operate AI Agents (Agentic AI Engineering)</p> <ul> <li>Design and implement AI Agent architectures (planner/executor patterns, multi-step reasoning flows, tool-use orchestration) to execute business tasks end-to-end. </li><li>Build tooling and integrations for agents (APIs, internal services, data tools, workflow engines), including secure action execution, approvals, and guardrails. </li><li>Engineer agent behaviors for reliability: deterministic fallbacks, bounded autonomy, retries, idempotency, and safe failure modes for partial completion. </li></ul> <p>Agent Platforms, Reuse, and Scale</p> <ul> <li>Develop reusable agent frameworks and components: shared tool registry, prompt/tool contracts, agent memory strategies, policy enforcement, and standardized observability. </li><li>Enable teams to embed agents into multiple products/channels via SDKs, reference implementations, and well-defined APIs, reducing duplication and improving consistency. </li><li>Implement evaluation pipelines for agents: task success rate, tool-call accuracy, groundedness, latency/cost, and regression testing across agent versions. </li><li>Build production-grade RAG pipelines and grounding mechanisms to ensure agent outputs are traceable and based on authoritative enterprise knowledge sources. </li><li>Implement agent memory patterns (session memory, long-term memory, semantic caches) with strong privacy and retention controls. </li><li></li></ul>