Software Engineer III, Applied Agentic AI

• Build reference agentic applications on our platform - end-to-end examples of how agents should be designed, evaluated, deployed and monitored at Proofpoint.
• Establish and document best practices: tool design and MCP integration, prompt and context management, memory and planning, cost/latency tradeoffs, failure recovery, and what "release-ready" means for a nondeterministic system.
• Design evaluation harnesses - task suites, baselines, and quality, cost and latency metrics - and use them to decide what ships.
• Turn ambiguous questions into working prototypes quickly, and present results to the teams who asked; recommend just as readily when an approach should be abandoned.
• Harden successful prototypes into reusable platform capabilities that product teams can adopt.
• Partner with experienced engineers, security researchers and product tech leads to go deep on the systems you build on.
• Socialize agentic patterns across the company through demos, design reviews, written guides, and pairing sessions.
• Communicate and understand stakeholders' requirements and participate in cross-team design discussions.

• Bachelors or Master's Degree in Computer Science or a related field, or equivalent practical experience.
• 3+ years of engineering experience, with recent hands-on work on LLM or agentic systems that went past the prototype stage.
• Good understanding of the agentic development lifecycle and its components - agent runtimes, tool and MCP integration, prompt and context management, memory, planning, orchestration, evals, tracing, guardrails, rollout and rollback.
• Solid Python; TypeScript/Node a plus.
• Experience working with globally distributed teams .
• Experience building and running services in a cloud microservices environment - containers, CI/CD, automated deployment; AWS a plus.
• Comfortable diagnosing distributed systems from traces and metrics; OpenTelemetry (including GenAI semantic conventions) a plus.
• An eval-first mindset: measurement comes with the build, not after it.
• Genuine enthusiasm for frontier AI - you already experiment with agent frameworks and LLM SDKs (LangGraph, Anthropic/OpenAI Agents SDK, MCP, LangChain or similar) and follow where the field is going.
• Initiative and a bias toward shipping - you pick up ambiguous problems, get a PoC working and presented in days rather than quarters, and keep moving when the path isn't mapped out.
• Fast learner with real curiosity - you want to know how the systems underneath you work, not just how to call them.

Preferred

• Use of AI coding tools (Claude Code, Codex or similar) and familiarity with agent interoperability protocols such as MCP and A2A.
• Building eval harnesses, benchmarks or ground-truth datasets.
• Producing developer-facing reference implementations, SDK samples, or internal enablement material.
• AG and semantic retrieval (vector stores, hybrid search), and working with both hosted APIs and open-weight models.

Why Proofpoint?

At Proofpoint, we believe that an exceptional career experience includes a comprehensive compensation and benefits package. Here are just a few reasons you'll love working with us:

• Competitive compensation

• Comprehensive benefits

• Career success on your terms

• Flexible work environment

• Annual wellness and community outreach days

• Always on recognition for your contributions

• Global collaboration and networking opportunities

Our Culture:

Our culture is rooted in values that inspire belonging, empower purpose and drive success-every day, for everyone. We encourage applications from individuals of all backgrounds, experiences, and perspectives. If you need accommodation during the application or interview process, please reach out to accessibility@proofpoint.com .