Remote AI Platform Engineer — Customer-Facing

Tenstorrent; United States; On-site; USD 100,000 - 500,000; Full time

Job summary

Tenstorrent is seeking a Forward Deployed Engineer to connect customers with our AI compute platform. You will write production code, manage deployments, and clearly communicate trade-offs between customer needs and engineering feasibility across the inference stack.

We welcome applicants at various levels; the role is remote, based in North America, with hubs in Santa Clara, Austin, or Toronto. Strong experience in Kubernetes, LLM serving, and observability will help you succeed.

Qualifications

• 5+ years of relevant software/ML engineering experience.
• Experience turning ambiguous customer requirements into verifiable criteria.
• Kubernetes and Helm experience at multi-node, HPC, or AI cluster scale.
• Observability and automation with Prometheus, Grafana, OpenTelemetry.

Responsibilities

• Develop production code and operate deployments for AI inference services.
• Bridge between customers, engineering, and AI products to ensure alignment.
• Explain trade-offs to customer leadership and core engineering teams.
• Work directly with customers to understand challenges and provide effective solutions.

Skills

Kubernetes

Helm

Prometheus

Grafana

OpenTelemetry

LLM inference serving

Customer collaboration

Tools

vLLM

SGLang

Mooncake

NIM

Dynamo

LMCache

Job description

Tenstorrent is seeking a Forward Deployed Engineer to connect customers with our AI compute platform. You will write production code, manage deployments, and clearly communicate trade-offs between customer needs and engineering feasibility across the inference stack.

We welcome applicants at various levels; the role is remote, based in North America, with hubs in Santa Clara, Austin, or Toronto. Strong experience in Kubernetes, LLM serving, and observability will help you succeed.