(Senior) Software Engineer, AI Infrastructure

What you'd do:

Design and implement autonomous agents for SRE, DevOps, and DBA workflows on Quartermaster.

Build robust agent loops with planning, reasoning, tool-use, error recovery, and escalation mechanisms.

Integrate agents with Kubernetes, Terraform, cloud APIs, monitoring platforms, databases, and CI/CD systems.

Define metrics and build evaluation frameworks to measure agent effectiveness and goal achievement.

Partner with SRE, DevOps, and platform teams to identify high-value automation workflows.

Contribute to technical vision for AI agents transforming infrastructure operations and bring new ideas.

What they want:

5+ years professional software engineering; proficiency in Python, Go, Java, or Kotlin.

Practical experience with AWS, GCP, Aliyun, Kubernetes, Terraform, and CI/CD infrastructure systems.

Strong system design skills to architect reliable, safe, scalable agent systems.

Excellent communication and collaboration skills; proven track record across cross-functional global teams.

Nice to have:

Experience designing and building agentic AI systems with LLMs and multi-step task planning.

Experience with agent orchestration frameworks like LangGraph, CrewAI, AutoGen, and LLM APIs.

Experience with Grafana, Prometheus, Datadog, ELK stack, or building agents that interact with them.

Experience with database administration, schema migrations, query optimization, and backup/recovery automation.

Understanding of SRE practices including incident response, runbooks, postmortems, SLOs, and SLIs.

Forward-thinking mindset on agent reliability, safety, evaluation, and increasingly autonomous systems.

5+ years professional software engineering; proficiency in Python, Go, Java, or Kotlin.

Practical experience with AWS, GCP, Aliyun, Kubernetes, Terraform, and CI/CD infrastructure systems.

Strong system design skills to architect reliable, safe, scalable agent systems.

Excellent communication and collaboration skills; proven track record across cross-functional global teams.

#J-18808-Ljbffr