← All roles
Member of Technical Staff, Model Efficiency
C++PythonRustGovLLMvLLMCUDADistributed Systems
About the role
As a Member of Technical Staff on the Model Efficiency team, you will work across the inference stack to improve core performance metrics, identify bottlenecks, and develop optimizations. You will collaborate with modeling and systems teams to accelerate inference, with opportunities to build expertise in GPU/CUDA optimizations, kernel-level improvements, and model execution strategies for MoE and large-scale architectures.
Requirements
5+ years of production-quality code, strong C++/Python, experience with LLM inference (vLLM, SGLang), ability to diagnose performance bottlenecks, bias for action. Plus: GPU/CUDA, MoE, speculative decoding, distributed systems.
About the company
Cohere
Cohere is a leader in the AI industry, providing enterprise-ready AI platforms and generative models that enhance workplace productivity and data insights. Their solutions, including North and Compass, empower businesses by leveraging advanced retrieval and natural language processing technologies. Cohere's value proposition lies in offering scalable, secure, and customizable AI solutions that keep data within the customer's infrastructure.
View company page →More from Cohere
Forward Deployed Engineer, Inference
KubernetesGCPAzureAWSvLLMPythonGoDistributed Systems
$240k–415k
Onsite · United States
Forward Deployed Engineer, Inference
$240k–415k
KubernetesGCPAzureAWSvLLMPythonGoDistributed Systems
Engineering Manager, Cohere APIs and DevEx
GoTypeScriptReact
CA$300k–375k
Remote · CA
Engineering Manager, Cohere APIs and DevEx
CA$300k–375k
GoTypeScriptReact
Senior/Staff Software Engineer (Back-End), Inference
GoPythonJavaC++RustDistributed Systems
$205k–315k
Remote · Worldwide
Senior/Staff Software Engineer (Back-End), Inference
$205k–315k
GoPythonJavaC++RustDistributed Systems
Product Security Engineer, North Security
PythonGoTypeScriptKubernetesOIDC
CA$230k–330k
Remote · Worldwide
Product Security Engineer, North Security
CA$230k–330k
PythonGoTypeScriptKubernetesOIDC
Data Engineer, Data Foundations
PythonApache SparkApache FlinkBigQueryApache AirflowJavaGoKubernetes
$160k–325k
Remote · CA, US
Data Engineer, Data Foundations
$160k–325k
PythonApache SparkApache FlinkBigQueryApache AirflowJavaGoKubernetes
Similar roles
Staff Software Engineer, Inference
$188k–275k
Staff Software Engineer, Inference
$188k–275k
Member of Technical Staff, Performance and Scale
$200k–400k
Member of Technical Staff, Performance and Scale
$200k–400k
Senior Backend Engineer, Inference Platform
$200k–290k
Senior Backend Engineer, Inference Platform
$200k–290k
Software Engineer, GPT Infrastructure
$293k–385k
Software Engineer, GPT Infrastructure
$293k–385k
Software Engineer, Inference AI/ML
$92k–135k
Software Engineer, Inference AI/ML
$92k–135k