Senior Software Engineer – Infra Agent Systems

This is a fully remote position, open to applicants in India.

📋 Description

• Design and develop production AI agent systems that diagnose, investigate, and resolve infrastructure issues across one of the largest GPU fleets globally.

• Create distributed services, orchestration frameworks, knowledge graphs, and retrieval systems that empower infrastructure agents.

• Build fleet intelligence systems that integrate telemetry, infrastructure state, operational knowledge, and historical incidents.

• Connect with observability, incident management, ticketing, fleet inventory, source control, chat, and internal infrastructure systems via APIs.

• Take ownership of services from start to finish, encompassing architecture, implementation, testing, deployment, observability, and production operations.

• Enhance agent performance through evaluations, retrieval enhancements, improved tools, and production feedback loops.

• Transform agents’ production insights into robust, reviewed software and automation.

• Deliver, operate, and provide support for software in a production environment.

⛳️ Requirements

• Over 5 years of experience in building production backend systems, distributed systems, or infrastructure platforms.

• Strong skills in systems design and experience in managing significant systems from design through to production.

• Expertise in at least one of the following areas: AI agent systems, orchestration, tool utilization, evaluation, or grounding; knowledge graphs or graph data modeling; search, retrieval, ranking, RAG, or semantic search systems.

• Proficient in backend engineering, particularly in API design, service boundaries, data modeling, and integrations within complex systems.

• Familiarity with Kubernetes, GitOps tools like ArgoCD, infrastructure-as-code, and cloud platforms.

• Comfortable programming in Go, TypeScript, Python, or Rust.

• Knowledge of GPU infrastructure, datacenters, bare-metal systems, hardware failure modes, BMC/IPMI, or cluster schedulers is advantageous.

• Experience with graph databases is a plus.

• Familiarity with event-driven systems and messaging platforms such as NATS or Kafka is a plus.

• Experience with observability platforms like Prometheus and Grafana is a plus.

• Background in building evaluation frameworks or enhancing the quality and reliability of LLM-powered systems is a plus.

🏝️ Benefits

• Competitive salary and performance-based bonuses.

• Comprehensive health, dental, and vision insurance.

• Flexible working hours and remote work options.

• Opportunities for professional development and training.

• Collaborative and innovative work environment.