“SGLang” jobs in Canada – Page 2

No matching filters. Try another name.

Results

• 1mo

  Software Engineer - Inference Platform

  Toronto, ON +1

  HybridFull Time

  

  Baseten

  3+ YOECandidates need 3+ years building distributed systems or large-scale backend APIs, with experience in low-latency services, observability and performance profiling. Kubernetes, GPU workloads and LLM inference experience are assets, but prior ML experience is not required.

  Kubernetes, GPU, vLLM, SGLang, TensorRT-LLM, NVIDIA Dynamo

  1mo

  Software Engineer - Inference Performance

  Toronto, ON +1

  HybridFull Time

  

  Baseten

  Candidates need a bachelor's, master's or PhD in a technical field, experience with Python or C++, and familiarity with LLM optimization and ML libraries such as PyTorch or TensorRT. They also need a deep understanding of GPU architecture and demonstrated interest in LLMs.

  PyTorch, TensorRT, TensorRT-LLM, vLLM, SGLang, CUDA

  1mo

  Technical Program Manager, Model Performance

  Toronto, ON +1

  HybridFull Time

  

  Baseten

  Candidates need deep technical program management experience on complex programs, and experience with model performance or inference optimization. They should be comfortable building programs from ambiguity and influencing people without authority.

  vLLM, TensorRT-LLM, SGLang, NVIDIA Dynamo

  1mo

  Software Engineer - GPU Networking & Distributed Systems

  Toronto, ON +1

  HybridFull Time

  

  Baseten

  Baseten needs deep experience with high-performance networking such as InfiniBand and RoCE v2, and fluency in C++ or Python. Candidates should understand NVIDIA GPU memory architecture and be comfortable debugging low-level systems.

  InfiniBand, RoCE, NCCL, NVSHMEM, NVLink, TensorRT-LLM

• 1mo

  Développeur.se - opérations liées à l’apprentissage automatique / MLOps Developer

  Vancouver, BC

  

  Electronic Arts

  8+ YOEElectronic Arts needs candidates with 8+ years of engineering experience, 4+ years running ML systems in production, strong Python skills, and experience with frameworks such as PyTorch and inference servers such as vLLM. Experience with distributed data processing, observability tools and AWS ML infrastructure is also needed.

  PyTorch, vLLM, SGLang, TensorRT-LLM, Ray, Spark

• 1mo

  Senior Technical VP - AI & Efficient Deep Learning

  Markham, ON

  On-siteFull Time

  

  Huawei Technologies Canada Co., Ltd.

  5+ YOECandidates need a degree in computer science, mathematics, statistics or engineering and deep knowledge of AI theory and large models. They also need 5+ years of AI experience, experience leading large-scale training or inference systems, and strong knowledge of AI chip architecture and distributed computing.

  Megatron, vLLM, SGLang

  1mo

  Co-op Software Engineer - AI System & Infrastructure

  Vancouver, BC

  $58k–$104k/yrOn-siteInternship

  

  Huawei Technologies Canada Co., Ltd.

  Candidates need a Bachelor's, Master's or PhD in Computer Science or Computer Engineering. They need experience building large, high-performance distributed systems, plus skills in GPU, container and AI serving technologies and in one or more programming languages.

  Kubernetes, TensorRT-LLM, NVIDIA TensorRT, NVIDIA Triton, PyTorch, CUDA

  1mo

  Principal Architect – Hardware Efficient AI Foundation Model Training

  Markham, ON

  On-siteFull Time

  

  Huawei Technologies Canada Co., Ltd.

  Candidates need experience training and deploying AI models of 10B+ parameters, knowledge of the latest AI architectures and frameworks such as PyTorch and vLLM, and understanding of AI chip architecture. A PhD is preferred, and publications in AI systems or chip design are an asset.

  PyTorch, vLLM, SGLang, GPU, NPU, TPU

  1mo

  Senior Researcher – Hardware Efficient AI Foundation Model Training

  Markham, ON

  On-siteFull Time

  

  Huawei Technologies Canada Co., Ltd.

  Candidates need experience training and deploying AI models of 10B+ parameters, knowledge of modern AI architectures such as long-sequence, reinforcement learning, multimodal and agent models, and solid command of AI frameworks and distributed training. Familiarity with AI chip architectures (GPU, NPU, TPU) is an asset, and a PhD and publications in AI systems or chip design are assets.

  PyTorch, vLLM, SGLang, GPU, NPU, TPU

  1mo

  Intern Researcher – AI Foundation Model Training

  Markham, ON

  On-siteInternship

  

  Huawei Technologies Canada Co., Ltd.

  Candidates need to be currently pursuing a PhD or Master's degree in computer science, electrical engineering or a related field. Familiarity with deep learning frameworks such as PyTorch and distributed training concepts is needed, with GPU or accelerator experience and research or open-source contributions as assets.

  PyTorch, vLLM, SGLang, GPU, NPU, TPU

  1mo

  Intern Engineer – RL Post-Training for LLMs

  Vancouver, BC

  On-siteInternship

  

  Huawei Technologies Canada Co., Ltd.

  Candidates need to be enrolled as a Master's or PhD student in computer science, AI or a related field, with a strong background in machine learning, reinforcement learning and deep learning. Proficiency in Python, PyTorch and LLM frameworks is required, and hands-on RL and LLM experience is an asset.

  PyTorch, Hugging Face, DeepSpeed, vLLM, SGLang, VeRL

  1mo

  Research Engineer - AI Workload & Systems

  Markham, ON

  On-siteContract

  

  Huawei Technologies Canada Co., Ltd.

  Candidates need a strong understanding of modern AI architectures and AI accelerator hardware such as GPUs and TPUs. Hands-on kernel development experience with CUDA or Triton, plus LLM inference and profiling experience, is required; a PhD is an asset.

  CUDA, Triton, TileLang, vLLM, SGLang, PyTorch

  1mo

  Co-op Researcher – LLM Post-Training & Agentic Coding

  Edmonton, AB

  On-siteInternship

  

  Huawei Technologies Canada Co., Ltd.

  Candidates need to be enrolled in a senior co-op program in computer science, machine learning or AI. They need strong Python and PyTorch skills, solid knowledge of large language models, and hands-on experience with ML research or systems.

  PyTorch, vLLM, SGLang, FSDP, DeepSpeed, Hugging Face

• 1mo

  Principal Engineer, Efficient GenAI

  Markham, ON

  Full Time

  AM

  Advanced Micro Devices, Inc

  Candidates need deep hands-on experience with generative AI models such as LLMs, 3D world models or image/video generation, plus large-scale model training. A PhD or Master's degree in a related field and several years of AI and deep learning experience are required.

  PyTorch, JAX, vLLM, SGLang, MuJoCo

  1mo

  AI Systems Engineer – AI Model (Training & Inference)

  Markham, ON

  Full Time

  AM

  Advanced Micro Devices, Inc

  Candidates need hands-on experience shipping LLMs on real hardware and writing GPU kernels that improved production performance. They also need experience building distributed AI infrastructure, plus a relevant bachelor's, master's or PhD in computer or software engineering or computer science.

  HIP, Triton, MLIR, ROCm, RCCL, Kubernetes

• 1mo

  Compute Solution Architect

  Montréal, QC +1

  RemoteFull Time

  

  Mistral

  5+ YOECandidates need 5 to 10+ years in cloud solutions, technical account management or customer engineering roles, plus hands-on AI/ML workload experience. Mistral also wants working knowledge of cluster orchestration tools such as Slurm and Kubernetes.

  Slurm, Kubernetes, PyTorch, JAX, TensorFlow, vLLM

• 1mo

  Développeur Senior Traitement de Données ML

  Montréal, QC

  

  LoiZéro

  5+ YOEDiplôme en informatique, génie logiciel ou domaine connexe; Plus de 5 ans d'expérience en traitement de données textuelles massives ou NLP; Expérience de Spark, Ray ou Flink pour le traitement distribué

  Python, Spark, Ray, Flink, Airflow, Prefect

• 1mo

  ML Research Scientist - Inference ML

  Canada

  Full Time

  

  Cerebras Systems

  3+ YOECandidates need a PhD in machine learning or computer science with 3+ years of experience, or a master's with 4+ years. They need strong research impact, deep knowledge of modern ML architectures, and strong Python skills with PyTorch.

  PyTorch, vLLM, SGLang, Triton, CUDA, Cerebras tools

  1mo

  Staff Software Engineer, Inference API

  Toronto, ON

  HybridFull Time

  

  Cerebras Systems

  5+ YOECandidates need 5+ years of software engineering experience with substantial individual-contributor ownership of production systems. Strong Python and Go, plus systems-language experience in C++ or Rust, and experience with streaming, REST or gRPC inference APIs on Linux, containers and Kubernetes are required.

  Kubernetes, vLLM, PyTorch, Hugging Face Transformers, ROCm, Triton

  1mo

  Staff Software Engineer, GPU Inference

  Toronto, ON

  HybridFull Time

  

  Cerebras Systems

  8+ YOECandidates need 8+ years of software engineering experience with ownership of complex production systems. Strong C++ and Python, LLM inference serving experience (such as vLLM or TensorRT-LLM) and GPU performance knowledge are required.

  vLLM, ROCm, HIP, PyTorch, Kubernetes, AMD Instinct GPUs

  1mo

  Software Engineer, GPU Inference

  Toronto, ON

  On-siteFull Time

  

  Cerebras Systems

  5+ YOECerebras Systems needs candidates with 5+ years of software engineering experience, including production inference work for large models. Strong C++ and Python, hands-on serving framework experience such as vLLM, and deep GPU performance knowledge are required.

  vLLM, ROCm, PyTorch, Kubernetes, AMD Instinct GPUs, RCCL

• 1mo

  Software Engineer, Machine Learning

  Vancouver, BC

  Full Time

  E

  Ema

  Ema needs candidates with deep, defensible experience in agent systems, post-training, reward modeling, RL environments, retrieval or evaluation design, plus statistical rigour and production engineering skill. A master's or PhD in a relevant field, or equivalent work or research experience, is accepted.

  TRL, veRL, OpenRLHF, vLLM, SGLang

• 1mo

  Senior ML Data Processing Developer

  Montréal, QC

  

  LawZero

  5+ YOECandidates need a degree in computer science, software engineering or a related field, and 5+ years of experience handling trillion-token text datasets in data processing, ML engineering or NLP. They also need hands-on work with distributed frameworks such as Spark, Ray or Flink, strong production Python, and experience with orchestration tools such as Airflow, Prefect or Dagster.

  Spark, Ray, Flink, Airflow, Prefect, Dagster

• 1mo

  Member of Technical Staff, Model Efficiency

  Toronto, ON +1

  $295k–$535k/yrRemoteFull Time

  

  Cohere: Cohere is the leading security-first enterprise AI company.

  5+ YOECandidates need 5+ years writing high-performance production code in C++ or Python, experience with LLM inference tools such as vLLM or SGLang, and a bias for shipping fast and measuring impact.

  vLLM, SGLang, CUDA

10 companies