Cohere
Member of Technical Staff, Model Efficiency
$250K–$535K
New York +3 · Remote · Staff · Full-time · Posted Nov 7, 2025
- Location
- New York
San Francisco
Toronto
Montreal - Experience
- 5+ years writing high-performance, production-quality code.
About the job
Improves production LLM inference efficiency by diagnosing execution bottlenecks and developing, measuring, and shipping optimizations across the inference stack.
What you'll do
- Analyze model execution and resolve performance bottlenecks across the inference stack.
- Collaborate with modeling and systems teams to test, measure, and deliver inference improvements.
- Develop expertise in GPU/CUDA, kernel-level, and model execution optimizations for MoE and large-scale architectures.
What they ask for
- 5+ years of experience writing high-performance, production-quality code.
- Strong programming skills in C++ or Python; Rust/Go also welcome.
- Experience with large language models and familiarity with the LLM inference ecosystem.
- Ability to diagnose and resolve performance bottlenecks across the model execution stack.
Nice to have
- GPU programming, CUDA, or low-level systems optimization.
- Transformer language modeling techniques or scaling performance-critical distributed systems.
Pay
CA$250K – CA$535K (base salary)
Tools
C++, Python, Rust, Go, vLLM, SGLang, CUDA
AI focus
Optimizes LLM inference performance, including latency, throughput, and quality across workloads.
Model-written summary · the original posting is authoritative