Senior Software Engineer, Infrastructure AI
Core
Design, build, and operate goal-oriented AI agents that autonomously execute SRE, DevOps, and DBA workflows on production infrastructure.
Role type
Senior IC Infrastructure AI Engineer (Agentic Systems)
Builds
Autonomous AI agents for incident response, infrastructure provisioning, deployment orchestration, and database management.
Domain
Global Payments / Financial Infrastructure / Agentic AI
Deliverable
production ML models
Required skills
Backend development (Python, Go, Java, Kotlin), Cloud platforms (AWS, GCP, Aliyun), Container orchestration (Kubernetes), Infrastructure-as-code (Terraform), CI/CD systems, System design, Agent architecture (planning, reasoning, tool-use, safety guardrails), Observability (Grafana, Prometheus, Datadog, ELK), Database operations, SRE practices.
Preferred skills
Agentic AI system design (LLM-based agents, loop design, state management), Agent orchestration frameworks (LangGraph, CrewAI, AutoGen), LLM APIs (OpenAI, Anthropic), Database administration automation, Incident response and postmortem analysis.
Technologies
Quartermaster, Kubernetes, Terraform, AWS, GCP, Aliyun, OpenAI, Anthropic, LangGraph, CrewAI, AutoGen, Grafana, Prometheus, Datadog, ELK, Python, Go, Java, Kotlin.
Responsibilities
Design and implement autonomous agents for SRE, DevOps, and DBA workflows; Build robust agent loops with planning, reasoning, and error recovery; Integrate agents with real infrastructure tooling (Kubernetes, Terraform, cloud APIs, databases); Define metrics and build evaluation frameworks for agent performance; Partner with SRE, DevOps, and platform teams to identify automation opportunities; Contribute to the technical vision for infrastructure AI.
Seniority
Senior, hands-on IC
