Senior Software Engineer — Infra Agent Systems
Together AI2 months ago
Amsterdam, NetherlandsSenior
Responsibilities
- Design and build production AI agent systems for diagnosing, investigating, and remediating infrastructure issues across a large GPU fleet.
- Build distributed services, orchestration frameworks, knowledge graphs, and retrieval systems for infrastructure agents.
- Develop fleet intelligence systems combining telemetry, infrastructure state, operational knowledge, and historical incidents.
- Integrate with observability, incident management, ticketing, fleet inventory, source control, chat, and internal infrastructure systems through APIs.
- Own services end to end across architecture, implementation, testing, deployment, observability, and production operations.
- Improve agent performance through evaluations, retrieval improvements, better tools, and production feedback loops.
- Convert production agent learnings into reliable, reviewed 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, grounding, knowledge graphs, graph data modeling, search, retrieval, ranking, RAG, or semantic search.
- Strong backend engineering experience with API design, service boundaries, data modeling, and integrations across complex systems.
- Experience with Kubernetes, GitOps such as ArgoCD, infrastructure-as-code, and cloud platforms.
- Comfort working with Go, TypeScript, Python, or Rust.
- Preferred experience includes GPU infrastructure, datacenters, bare-metal systems, hardware failure modes, BMC/IPMI, cluster schedulers, graph databases, NATS, Kafka, Prometheus, Grafana, and LLM evaluation or reliability improvement.
Benefits
- Hybrid work arrangement in Amsterdam.
Tech Stack
Categories
About Together AI
Together AI builds an AI-native cloud platform for developers, offering high-performance inference, fine-tuning/model shaping, and large-scale pre-training on on-demand GPU clusters with APIs and managed services. It emphasizes open-source models that teams can run and adapt, and also provides infrastructure for decentralized and scalable workloads. Founded in 2022 and headquartered in San Francisco, it is privately held and reports notable customers including Cursor, ElevenLabs, Salesforce, and Zoom.