Senior Software Engineer — Infra Agent Systems UK
Salary not listed • London • Full-time
Posted 2mo ago
This job has been open for more than 60 days. It may no longer be actively hiring, so check with the company before putting a lot into an application.
Remote Work Policy
On-site
Employment Type
Full-time
Categories
AI Agent Engineer
About the job
The Infra Agent Systems team builds the software systems that power and automate Together AI's large GPU fleet. This role involves developing production AI agents that diagnose hardware failures, investigate incidents, correlate signals, and automate operational workflows. You will also build the platform these agents run on, including knowledge graphs, retrieval systems, orchestration frameworks, and developer tooling. This is an opportunity to work at the intersection of AI agents, distributed systems, infrastructure, and automation, solving challenging engineering problems with real production impact. You will be responsible for delivering software and operating it in production.
Responsibilities
- Design and build production AI agent systems to diagnose, investigate, and remediate infrastructure issues.
- Build distributed services, orchestration frameworks, knowledge graphs, and retrieval systems for infrastructure agents.
- Develop fleet intelligence systems that combine telemetry, infrastructure state, and historical data for better agent decision-making.
- Integrate with observability, incident management, ticketing, and other internal infrastructure systems via APIs.
- Own services end-to-end, including architecture, implementation, testing, deployment, and production operations.
- Improve agent performance through evaluations, retrieval enhancements, and feedback loops.
- Convert learnings from agents in production into reliable software and automation.
Requirements
- 5+ years of experience building production backend systems, distributed systems, or infrastructure platforms.
- Strong systems design skills and experience owning significant systems from design through production.
- Depth in AI agent systems, orchestration, tool use, evaluation, or grounding.
- Depth in knowledge graphs or graph data modeling.
- Depth in search, retrieval, ranking, RAG, or semantic search systems.
- Strong backend engineering experience, including API design, service boundaries, and data modeling.
- Experience with Kubernetes, GitOps (e.g., ArgoCD), infrastructure-as-code, and cloud platforms.
- Comfort working with languages such as Go, TypeScript, Python, or Rust.
- Experience with GPU infrastructure, datacenters, or bare-metal systems is a plus.
- Experience with graph databases is a plus.
- Experience with event-driven systems and messaging platforms (e.g., NATS, Kafka) is a plus.
- Experience with observability platforms (e.g., Prometheus, Grafana) is a plus.
- Experience building evaluation frameworks or improving LLM-powered systems is a plus.