Staff Forward Deployed Engineer
Core
Bridge customers, engineering, and AI inference service products by creating continuity and solving hard problems at the edge of the stack.
Role type
Staff Forward Deployed Engineer (high-autonomy IC)
Builds
Production AI inference services and agentic workflows on Tenstorrent hardware
Domain
AI hardware/software co-design, LLM inference serving, Kubernetes clusters
Deliverable
production ML models | infrastructure
Required skills
accelerator compute/memory/networking topology expertise, LLM inference serving engines (vLLM, SGLang, Mooncake, NIM, Dynamo, LMCache), Kubernetes/Helm at HPC/AI cluster scale, observability/infrastructure automation (Prometheus, Grafana, OpenTelemetry), debugging full inference stack, translating ambiguous requirements to acceptance criteria
Preferred skills
early adoption of AI for agentic workflows, building reproducible benchmarks and telemetry
Technologies
RISC-V, Kubernetes, Helm, Prometheus, Grafana, OpenTelemetry, vLLM, SGLang, Mooncake, NIM, Dynamo, LMCache
Responsibilities
Debug across the full inference stack from failing requests to kernel dispatch, work directly with customers to understand challenges and provide solutions, contribute production code and operate deployments, bring feedback via pull requests and telemetry data
Seniority
Staff, hands-on IC with strategic customer impact
