Senior Llm Serving Optimization Engineer
24 hours ago
Winnipeg MB, Winnipeg Census Division, MB; Manitoba, Canada
Capgemini Engineering
Full-time
Free with email or Google
Save this job and keep your search organized
Create a free account to save jobs, create alerts and return to this listing from your dashboard.
Free with email or Google
By continuing, you agree to our Terms & Privacy Policy.
Optimize LLM serving as a senior machine learning systems engineer, working remotely across Canada with vLLM, PyTorch, and accelerator workloads. The mandate spans production inference.
Capgemini Engineering’s engineer extends model coverage and tunes inference behavior across AWS Neuron and Trainium platforms. You will read and modify implementations involving attention, mixture-of-experts routing, and KV-cache management. Responsibilities include hybrid state-space models, kernel-level optimization, and clear communication of engineering trade-offs.
Key Responsibilities
Extend model coverage across hybrid and mixture-of-experts architecturesReuse and generalize existing inference implementations where practicalOptimize prefill, decode, batching, and parallelism behaviorProfile framework, compiler, or kernel-level accelerator workloadsDocument implementation choices and benchmark reproducibilityRequirements:
Strong Python and PyTorch skills with model implementation experienceHands-on LLM serving framework experience such as vLLMDeep understanding of LLM inference performance trade-offsExperience designing rigorous performance experimentsKernel development using NKI, Triton, or CUDA preferredUse LLM serving, model architecture, and accelerator optimization expertise to advance production inference systems at Capgemini Engineering.
#J-18808-Ljbffr
Capgemini Engineering’s engineer extends model coverage and tunes inference behavior across AWS Neuron and Trainium platforms. You will read and modify implementations involving attention, mixture-of-experts routing, and KV-cache management. Responsibilities include hybrid state-space models, kernel-level optimization, and clear communication of engineering trade-offs.
Key Responsibilities
Extend model coverage across hybrid and mixture-of-experts architecturesReuse and generalize existing inference implementations where practicalOptimize prefill, decode, batching, and parallelism behaviorProfile framework, compiler, or kernel-level accelerator workloadsDocument implementation choices and benchmark reproducibilityRequirements:
Strong Python and PyTorch skills with model implementation experienceHands-on LLM serving framework experience such as vLLMDeep understanding of LLM inference performance trade-offsExperience designing rigorous performance experimentsKernel development using NKI, Triton, or CUDA preferredUse LLM serving, model architecture, and accelerator optimization expertise to advance production inference systems at Capgemini Engineering.
#J-18808-Ljbffr