As AI agents increasingly write and operate infrastructure, reliability systems must be able to reason and act at machine speed. In this role, you will set the technical direction and drive execution for an AI agent that autonomously gathers context, investigates incidents, identifies likely root causes, builds a safe mitigation plan, and executes it - with humans supervising and able to intervene at any point.
The immediate challenge is building an agent that is both highly accurate and broadly trusted. Experienced incident responders need a transparent collaborator that helps them investigate, continuously surfaces relevant evidence, and keeps them in control. Engineers who encounter incidents only occasionally need an agent that leads the investigation and guides them to a safe outcome.
You will lead two tightly connected areas:
- Agent quality - skills, tools, context, memory, offline evaluation, backtesting, online experimentation, and learning from production outcomes.
- Responder experience - a multi-turn interface that gives responders visibility into the agent's work and brings together the operational data they need to make decisions.
This is a deeply hands-on technical leadership role at the intersection of large-scale distributed systems, incident response, applied AI, and product engineering. You will personally design and ship critical parts of the system while leading senior engineers across team and organizational boundaries. The long-term opportunity is to help create self-healing infrastructure that resolves production incidents safely at Meta scale.
Responsibilities
- Define and drive the technical vision, architecture, and execution roadmap for AI-powered incident investigation and mitigation
- Personally design, code, evaluate, and ship major capabilities in a production agentic system
- Improve timely root-cause accuracy through better reasoning, skills, tool use, context, memory, planning, and domain knowledge
- Build the offline evaluation, historical replay, and online experimentation systems needed to measure changes and continuously improve agent behavior
- Create a transparent, multi-turn experience that supports collaborative investigation with expert responders and agent-led guidance for less frequent responders
- Enable the agent to reason across telemetry, code, configuration, deployments, service dependencies, operational knowledge, and incident history
- Build closed-loop learning systems that turn production outcomes and user feedback into evaluations, experiments, and product improvements
- Advance the system toward progressive autonomy with explicit authorization, validation, auditability, rollback, and human oversight
- Build an extensible platform that combines shared capabilities with domain-specific skills, tools, and agents contributed by infrastructure and product teams
- Partner closely with on-call engineers, reliability experts, product groups, data science, and product management to drive accuracy, adoption, and realized operational impact
- Ensure the system meets a high bar for reliability, latency, scale, security, privacy, and cost
- Influence technical strategy across organizations and mentor senior engineers working across distributed systems and applied AI
Qualifications
- Bachelor's degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience
- 10+ years of software engineering experience, including experience building and operating large-scale distributed, infrastructure, or production AI systems
- Experience setting technical direction and leading complex engineering efforts across multiple teams or organizational boundaries
- Experience applying AI to production problems at scale, including evaluation of system quality and failure modes
- Recent hands-on experience designing, coding, debugging, and shipping complex production systems
- Experience building systems that support critical, always-on production workloads
- Experience diagnosing complex production systems using telemetry, code, configuration, deployments, and dependency information
- Experience translating customer needs into technical architecture and driving adoption of a platform or developer product
- Experience coding in languages such as C++, Java, Python, Rust, or equivalent
- Experience influencing senior engineers and leaders without direct organizational authority Experience improving agent quality through context engineering, skills, memory, evaluation, automated experimentation, hill climbing, fine-tuning, or reinforcement learning
- Demonstrated ability to integrate AI tools to optimize/redesign workflows and drive measurable impact (e.g., efficiency gains, quality improvements)
- Experience building multi-turn, human-agent experiences for complex or high-stakes workflows
- Experience building production AI agents that use tools and reason across telemetry, code, configuration, deployments, and operational knowledge
- Track record of taking an ambitious technical product from early adoption to trusted, broad production use
- Experience designing autonomous or semi-autonomous production actions with identity, authorization, independent validation, auditability, rollback, and escalation
- Experience adhering to and implementing responsible, ethical AI practices (e.g., risk assessment, bias mitigation, quality and accuracy reviews)
- Experience with incident management, SRE, observability, on-call operations, or automated remediation at significant scale
- Demonstrated ongoing AI skill development (e.g., prompt/context engineering, agent orchestration) and staying current with emerging AI technologies
- Experience building extensible platforms that allow domain teams to contribute specialized capabilities while preserving a coherent user experience