Canonical page: https://taskbull.si/AIJobs/jobs/cohere-forward-deployed-engineer-inference/

[← Back to the shortlist](https://taskbull.si/AIJobs/#jobs) C Cohere Curated employer source

# Forward Deployed Engineer, Inference

United States · On-site · City not specified

Kubernetes vLLM Distributed serving Python / Go / C++

THE OPPORTUNITY

## A role wortha closer look.

Architect model-serving systems inside enterprise customer infrastructure. This senior role tackles multi-cluster deployment, routing, failover, accelerator validation and performance diagnosis. Engineers bridge Cohere’s core teams and strategic customers, making inference workloads more reliable and efficient while turning field problems into improvements to the underlying platform.

### Experience highlighted by the employer

- At least eight years operating production infrastructure, distributed systems or complex enterprise deployments.
- Bring deep Kubernetes and inference-stack experience, with strong programming foundations and customer-facing technical leadership.

### Location & eligibility

The vacancy specifies on-site work in the United States but does not name a city. Confirm the actual office or customer location and US authorization requirements before applying.

### Compensation

USD $240,000–$325,000 base / year*. US base range varies: $265,000–$325,000 in California, New York and Washington; $240,000–$295,000 in other states. Equity is additional. A separate Canadian tier appears in ATS compensation, but the vacancy location is US-only.

### Before you apply

This is TaskBull’s concise summary, not the employer’s full job description. Review the complete responsibilities, terms, accessibility information and privacy notice on the original application page.

[Read the full employer listing ↗](https://jobs.ashbyhq.com/cohere/8df498e9-aba8-487f-80ba-362b492bad09)

YOUR NEXT STEP

## Make yourwork count.

Apply directly with Cohere. Your application stays with the employer and its hiring platform.

[Apply with employer ↗](https://jobs.ashbyhq.com/cohere/8df498e9-aba8-487f-80ba-362b492bad09) Employer Cohere Work arrangement Onsite Source checked 2026-10-30 Employer posting date 2026-10-28 Review window ends 2026-11-13 The review date is our freshness limit, not the employer’s application deadline.

[Report a closed or changed role ↗](mailto:info.taskbull@gmail.com?subject=AIJobs%20listing%20update%3A%20cohere-forward-deployed-engineer-inference)