
Senior Software Engineer — Infra Agent Systems at Together AI
AI-native cloud platform for scalable inference, model shaping, and pre-training.
Build production AI agents and the core platform that operate and automate a massive GPU fleet; scope spans incident diagnosis, remediation, distributed services, orchestration, knowledge graphs, retrieval, fleet intelligence, integrations with observability/ticketing/source control/chat/internal systems, and end-to-end ownership through production ops; 5+ years building production backend/distributed/infrastructure systems; must have strong systems design plus backend API/service boundary/data modeling/integration experience; must have experience with Kubernetes, GitOps/IaC, and cloud platforms; comfortable with Go, TypeScript, Python, or Rust; depth needed in at least one of: AI agent systems/orchestration/evaluation/grounding, knowledge graphs/graph data modeling, or search/retrieval/ranking/RAG/semantic search; bonus: GPU/datacenter/bare-metal/BMC-IPMI/cluster scheduler experience, graph databases, event-driven systems/NATS/Kafka, Prometheus/Grafana, evaluation frameworks or improving LLM system reliability
Remote United States only



