About this role
Developing production AI agents and core platforms allows engineers to diagnose hardware failures, investigate incidents, and automate operational workflows for a massive GPU fleet. The Infra Agent Systems team at Together AI builds the software systems that power and automate this infrastructure, focusing on knowledge graphs, retrieval systems, orchestration frameworks, and developer tooling.
Engineers in this role tackle the dual challenge of making AI agents trustworthy enough for production infrastructure while building the distributed systems that support them. The ideal candidate brings strong backend engineering fundamentals and a desire to shape autonomous infrastructure from the ground up in a hybrid work environment based in Amsterdam.
What you will do
- Design and build production AI agent systems that diagnose, investigate, and remediate infrastructure issues across a large GPU fleet.
- Build distributed services, orchestration frameworks, knowledge graphs, and retrieval systems that power infrastructure agents.
- Develop fleet intelligence systems that combine telemetry, infrastructure state, operational knowledge, and historical incidents.
- Integrate with observability, incident management, ticketing, fleet inventory, source control, chat, and internal infrastructure systems via APIs.
- Own services end to end, covering architecture, implementation, testing, deployment, observability, and production operations.
- Improve agent performance through evaluations, retrieval enhancements, better tooling, and production feedback loops.
- Turn production learnings from agents into reliable, reviewed software and automation.
What you need
- Bring at least five years of professional experience building production backend systems, distributed systems, or infrastructure platforms.
- Demonstrate strong systems design skills with a track record of owning significant systems from design through production.
- Possess depth in AI agent systems, orchestration, tool use, evaluation, grounding, knowledge graphs, graph data modeling, or search and retrieval systems.
- Show strong backend engineering experience including API design, service boundaries, data modeling, and integrations across complex systems.
- Have hands-on experience with Kubernetes, GitOps tools like ArgoCD, infrastructure-as-code, and cloud platforms.
- Demonstrate comfort working across programming languages such as Go, TypeScript, Python, or Rust.
Nice to have
- GPU infrastructure, datacenters, bare-metal systems, hardware failure modes, BMC/IPMI, or cluster schedulers
- Graph databases
- Event-driven systems and messaging platforms such as NATS or Kafka
- Observability platforms such as Prometheus and Grafana
- Building evaluation frameworks or improving the quality and reliability of LLM-powered systems
Skills and tech stack
Questions candidates ask
What is the remote work policy?
The role is hybrid and based in Amsterdam.
What kind of systems will I be building?
You will build production AI agents and the core platform they run on, including knowledge graphs, search and retrieval systems, orchestration frameworks, and developer tooling to operate a massive GPU fleet.
What programming languages are used in this role?
Engineers are comfortable working across languages such as Go, TypeScript, Python, or Rust.