• Build and evolve the agent harness and orchestration that turns an LLM into a reliable autonomous pentester, the loop that reasons over an application, forms attack hypotheses, acts, and verifies results. • Design the tools and tool-shaped feedback the agent uses to probe and exploit, and the structured-output and validation layers that keep it reliable (e.g., hook-enforced mandatory validation, schema-constrained outputs). • Translate the team's offensive expertise into repeatable agent capabilities — partnering directly with our attackers to encode how they think into something the agent can do consistently. • Own and grow our evaluation infrastructure: benchmark suites, a failure-mode taxonomy across the pipeline (discovery → hypothesis → exploitation → verification), and regression detection, so we actually know whether the agent is getting better. • Manage LLM inference in production: model selection, prompt and context engineering, and keeping cost and latency under control (we run on AWS Bedrock with centralized cost tracking). • Hold the line on production-safety and no-false-positives, every finding the agent reports has to be real and reproducible.

• Help us grow and harden our browser automation and crawling engine • Advance our browser-driven crawler using Playwright and Stagehand • Tackle modern web app challenges: SPA routing, multi-step flows, etc. • Extend agentic login and authentication capabilities • Improve crawl coverage, determinism, and throughput • Collaborate with attack-team engineers to shape application maps

• Collaborate with cross-functional teams — including product managers and leadership — to shape long-term technical strategy and translate business requirements into customer-centric solutions. • Contribute to roadmap planning and partner with the team to drive execution and delivery. • Design and architect simple, cost-effective solutions to complex features with a focus on security, scalability, and performance—designed to work seamlessly across both our cloud and self-hosted environments. • Write production-quality code across our full stack (Angular/TypeScript, Node.js, and Go for API development). • Extend our SDK and providers to enable Pulumi Cloud functionality across multiple languages, including TypeScript/JavaScript, Go, Python, C#, and Java. • Participate in code and design reviews, sharing expertise and mentoring engineers across the team.

• Define the technical vision and development standards for APIs, SDKs and AI platform services. • Lead the architecture of complex solutions, ensuring that orchestration of agents and AI services is scalable and enterprise-grade resilient. • Serve as a technical advisor to leadership and squads, supporting decision-making on emerging technologies and cloud-native infrastructure. • Advocate engineering best practices (Clean Code, Design Patterns, Security) and a culture of quality across the Data & AI directorate. • Design and optimize technical governance to ensure distributed systems meet strict observability and security requirements. • Identify and mitigate structural technical risks before they impact operations or the AI product roadmap.