Lead AI-Agent Infra Engineer for Production Reliability

Meta; Boise (ID); On-site; USD 271,000 - 347,000; Full time

Job summary

Meta seeks a senior Software Engineer to build AI-powered reliability systems across large-scale distributed infrastructure. You will prototype and ship an autonomous agent that investigates production incidents, suggests safe mitigations, and executes them under supervision.

You will push the agent's capability through learning, tool use, and optimization while collaborating with stakeholders to apply AI across incident prevention, observability, and infrastructure operations at scale.

Qualifications

• Bachelor's degree or equivalent practical experience in CS/engineering.
• 12+ years of software engineering experience, including large-scale distributed or infrastructure systems.
• Experience setting technical direction and leading multi-year efforts across org.
• Experience applying AI/ML to production problems.
• Demonstrated experience moving from concept to production impact.
• Experience diagnosing complex production systems using telemetry, code, config, and dependencies.
• Experience coding in C++, Java, Python, Rust, or equivalent.
• Hands-on experience building and shipping complex production systems.
• Experience influencing senior engineers and leaders without direct authority.

Responsibilities

• Define the technical vision and architecture for agentic reliability systems across Meta.
• Design, code, and ship production agentic systems for infrastructure problems.
• Lead development of an AI agent for production incident investigation and mitigation.
• Improve agent reasoning, context, tool use, planning, evaluation, learning, and safe execution.
• Apply techniques like fine-tuning, reinforcement learning, distillation, pruning, and inference optimization.
• Identify new high-value AI applications across incident prevention, detection, mitigation, observability, and infrastructure operations.
• Move from problems to prototypes and validate on real workloads.
• Build evaluation systems linking agent quality to outcomes.
• Create guardrails for production actions with authorization and human oversight.

Skills

Distributed systems

Incident response

Applied AI

Production systems

Leadership

Mentoring

C++

Java

Python

Rust

Education

Bachelor's degree

Tools

Telemetry

Job description

Meta seeks a senior Software Engineer to build AI-powered reliability systems across large-scale distributed infrastructure. You will prototype and ship an autonomous agent that investigates production incidents, suggests safe mitigations, and executes them under supervision.

You will push the agent's capability through learning, tool use, and optimization while collaborating with stakeholders to apply AI across incident prevention, observability, and infrastructure operations at scale.