Cohere
Forward Deployed Engineer, Inference
$240K–$415K
United States · On-site · Full-time · Posted Oct 28, 2026
- Experience
- 8+ years of engineering experience in production infrastructure, large-scale distributed systems, or enterprise software deployment.
About the job
Leads customer-specific deployment and optimization of Cohere’s inference systems, ensuring models perform reliably, securely, and efficiently in enterprise environments.
What you'll do
- Architect and implement model-serving topologies, including multi-tenant serving, model routing, and cross-datacenter failover.
- Benchmark and profile customer workloads, troubleshoot performance issues, and support hardware validation.
- Guide production deployment and reliability practices, and relay customer feedback to core product teams.
What they ask for
- Deep production Kubernetes experience, including multi-cluster and hybrid/multi-cloud environments.
- Strong understanding of LLM architecture and inference performance dynamics.
- Hands-on experience with modern inference engines and optimization stacks.
- Strong programming foundations in Python, Go, or C++.
Pay
$240K – $415K USD total pay
Tools
Kubernetes, GCP, Azure, AWS, OCI, vLLM, TensorRT-LLM, Python
AI focus
Deploys, serves, benchmarks, and optimizes large language models for enterprise inference workloads.
Model-written summary · the original posting is authoritative