Staff Forward Deployed Engineer
TenstorrentVisit Tenstorrent website
Tenstorrent is an AI-computing company that sells AI hardware and licenses AI and RISC-V intellectual property.
Toronto, Canada
Funding history
Investors
About Tenstorrent
Tenstorrent builds computers for AI, including AI processors, scalable server systems, and open-source software and compiler tooling. It also licenses AI and RISC-V IP for customers building customized silicon.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will work with customers to turn requirements and issues into verifiable acceptance criteria. You will contribute production code, operate AI inference deployments, debug the full inference stack, and provide reproducible code, benchmarks, and telemetry that help improve deployments and products.
Requirements
- 5+ years of relevant technical experience.
- Experience translating ambiguous customer requirements or issues into verifiable acceptance criteria.
- Kubernetes and Helm experience at multi-node, HPC, or AI-cluster scale.
- Experience with observability and infrastructure automation, including Prometheus, Grafana, or OpenTelemetry.
- Experience with LLM inference serving engines and technologies, including vLLM, SGLang, Mooncake, NIM, Dynamo, or LMCache.
Responsibilities
- Work directly with customers to understand challenges and provide effective solutions.
- Contribute production code and operate deployments.
- Debug the full inference stack from failing requests through serving layers, memory failures, and kernel dispatch.
- Translate customer requirements and issues into verifiable acceptance criteria.
- Provide pull requests, reproducible code, benchmarks, and telemetry data.