• Build a centralized reliability command center that gives teams a unified view of system health, risk, and reliability across services and environments • Create AI agents that can assist with incident triage, root-cause exploration, log/trace summarization, and recommended next actions • Create developer-facing features and APIs that help engineers explore data, debug issues, and make better decisions • Use AI-assisted development tools (e.g., Cursor, Claude, Copilot) as leverage to prototype, refactor, and ship high-quality code quickly • Own projects end-to-end: requirements, architecture, implementation, testing, rollout, and iteration based on feedback • Collaborate closely with partner teams (Product, Infra, Data, SRE) to understand pain points and translate them into simple, powerful solutions

• Build a centralized reliability command center that gives teams a unified view of system health, risk, and reliability across services and environments • Create AI agents that can assist with incident triage, root-cause exploration, log/trace summarization, and recommended next actions • Create developer-facing features and APIs that help engineers explore data, debug issues, and make better decisions • Use AI-assisted development tools (e.g., Cursor, Claude, Copilot) as leverage to prototype, refactor, and ship high-quality code quickly • Own projects end-to-end: requirements, architecture, implementation, testing, rollout, and iteration based on feedback • Collaborate closely with partner teams (Product, Infra, Data, SRE) to understand pain points and translate them into simple, powerful solutions

• Evaluate, implement, and guide the effective use of AI tools within the software development lifecycle. • Establish best practices for AI development, coding assistance, coding agents, AI testing, documentation, debugging, and engineering workflow optimization. • Train engineers to become "architects of intent" rather than just writers of code—focusing on providing clear, high-level, context-rich goals, constraints, and validation criteria for AI agents to execute. • Institutionalize a culture of validation, requiring human engineers to thoroughly review, test, and understand AI-generated code to reduce risk of production issues. • Deploy multi-agent workflows using dedicated agent teams (e.g., separate agents for planning, coding, and testing) operating in parallel to automate end-to-end tasks like PR generation, refactoring, or legacy modernization. • Integrate agents directly into error monitoring systems and bug reporting (Jira) to automatically ingest stack traces, locate the root cause across the codebase, and generate a verified PR with a corresponding regression test prior to engineering triaging the ticket. • Prioritize refactoring for high modularity, deterministic testing, and explicit documentation to ensure agents can navigate, understand, and safely modify code, treating codebase health as the foundation for AI capability. • Mentor members of the Engineering team, supporting their growth, accountability, and day-to-day effectiveness using AI tools. • Partner closely with Product Management, CX leaders, and other stakeholders to translate business needs into high-quality technical solutions. • Ensure AI development meets a high bar for software quality, security, scalability, and reliability. • Design scalable AI/ML pipelines using LLMs, RAG, and agentic frameworks and integrate AI APIs into customer-facing applications and workflows. • Develop reusable accelerators, templates, and reference architectures to be leveraged by the broader engineering team.

• Evaluate, implement, and guide the effective use of AI tools within the software development lifecycle. • Establish best practices for AI development, coding assistance, coding agents, AI testing, documentation, debugging, and engineering workflow optimization. • Train engineers to become "architects of intent" rather than just writers of code—focusing on providing clear, high-level, context-rich goals, constraints, and validation criteria for AI agents to execute. • Institutionalize a culture of validation, requiring human engineers to thoroughly review, test, and understand AI-generated code to reduce risk of production issues. • Deploy multi-agent workflows using dedicated agent teams (e.g., separate agents for planning, coding, and testing) operating in parallel to automate end-to-end tasks like PR generation, refactoring, or legacy modernization. • Integrate agents directly into error monitoring systems and bug reporting (Jira) to automatically ingest stack traces, locate the root cause across the codebase, and generate a verified PR with a corresponding regression test prior to engineering triaging the ticket. • Prioritize refactoring for high modularity, deterministic testing, and explicit documentation to ensure agents can navigate, understand, and safely modify code, treating codebase health as the foundation for AI capability. • Mentor members of the Engineering team, supporting their growth, accountability, and day-to-day effectiveness using AI tools. • Partner closely with Product Management, CX leaders, and other stakeholders to translate business needs into high-quality technical solutions. • Ensure AI development meets a high bar for software quality, security, scalability, and reliability. • Design scalable AI/ML pipelines using LLMs, RAG, and agentic frameworks and integrate AI APIs into customer-facing applications and workflows. • Develop reusable accelerators, templates, and reference architectures to be leveraged by the broader engineering team.