“TensorRT-LLM” jobs in Canada

No matching filters. Try another name.

Results

• 2d

  GPU Infrastructure Engineer

  Remote in Canada

  $150k–$190k/yrRemoteFull Time

  P

  Polargrid

  Candidates need experience operating distributed, high-availability systems across sites and running bare-metal GPU fleets. They also need strong networking skills (BGP, DNS, TCP/TLS, load balancing), LLM inference engine experience, and automation or tooling skills in Go or Rust.

  InfiniBand, RDMA, vLLM, SGLang, TensorRT-LLM

  2d

  Backend Engineer

  Remote in Canada

  $100k–$150k/yrRemoteFull Time

  P

  Polargrid

  Candidates need experience running production backend services in Python, Go or Rust, including on-call work. They should have worked with open-source model inference backends, bare-metal Linux, infrastructure as code, CI pipelines, DNS or load balancing.

  Linux, vLLM, SGLang, TensorRT-LLM, llama.cpp, Triton Inference Server

• 3d

  AI Engineer

  Cambridge, ON

  

  Eclipse Automation

  5+ YOECandidates need five or more years of building production enterprise applications, hands-on experience with AI/LLM solutions such as RAG and agents, and experience with React, TypeScript, Python and either .NET/C# or Node.js. Strong SQL, API integration, and a degree or diploma or equivalent experience are also required.

  Ollama, llama.cpp, vLLM, NVIDIA NIM, Azure DevOps, GitHub Actions

• 8d

  Senior Machine Learning Systems Engineer, LLM Inference Performance on AWS Trainium

  Toronto, ON

  $72k–$139k/yr

  

  Capgemini

  5+ YOECandidates need 5+ years in machine learning or systems engineering, with 2+ years on production model inference. They must be strong in Python and PyTorch and have hands-on experience with an LLM serving framework.

  PyTorch, vLLM, AWS Trainium, AWS Neuron SDK, TensorRT-LLM, SGLang

• 9d

  Senior Software Engineer, ML API – AI Inference

  Toronto, ON

  HybridFull Time

  

  Cerebras Systems

  5+ YOECandidates need 5+ years of software engineering experience, strong Python and a production language such as Go, C++ or Rust, and experience building production APIs and operating services on Linux with containers and Kubernetes.

  Kubernetes, vLLM, PyTorch, Hugging Face Transformers, LLGuidance, CUDA

  29d

  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

• 10d

  Member of Technical Staff (Software Engineer, GPU Cluster Infrastructure)

  Toronto, ON

  Full Time

  

  Perplexity

  Candidates need deep Kubernetes experience, including custom operators and multi-cluster work, and experience managing GPU clusters at scale. They also need multi-cloud orchestration, distributed systems fundamentals, and systems programming in Go, Rust or C++.

  Kubernetes, CUDA, InfiniBand, RoCE, Slurm, Prometheus

• 22d

  Founding Sales Engineer

  Toronto, ON +4

  RemoteFull Time

  

  Featherless AI

  3+ YOECandidates need 3 to 6 years in pre-sales engineering, solutions architecture or customer-facing engineering, with hands-on Python and working knowledge of LLM inference serving. Featherless AI also expects familiarity with the open-model ecosystem, containers and Kubernetes, and clear written communication.

  Python, Kubernetes, Hugging Face, vLLM, SGLang, TensorRT-LLM

• 26d

  Founding Sales Engineer

  Toronto, ON

  Full Time

  

  Urban Ridge Supplies

  3+ YOECandidates need 3 to 6 years in pre-sales engineering, solutions architecture or customer-facing engineering in AI, cloud or developer tooling. They must write Python, understand LLM inference serving and open-model ecosystems, and communicate well in writing and in meetings.

  Python, Kubernetes, Hugging Face, vLLM, SGLang, TensorRT-LLM

  26d

  Founding Sales Engineer

  Toronto, ON

  Full Time

  

  Urban Ridge Supplies

  3+ YOECandidates need 3 to 6 years in pre-sales engineering, solutions architecture or customer-facing engineering, with hands-on Python skills. They should know LLM inference serving, open-model ecosystems, containers and Kubernetes.

  Python, Kubernetes, HubSpot, Hugging Face, vLLM, SGLang

• 26d

  Research Engineer - AI Systems

  Remote in Canada

  RemoteFull Time

  

  Yotta Labs

  Candidates need strong Python and C++ skills, deep GPU architecture knowledge and experience with CUDA, Triton, ROCm or AWS Neuron. A background in computer science or engineering is preferred, along with the ability to work collaboratively in a remote team.

  CUDA, Triton, ROCm, AWS Neuron SDK, PyTorch, Nsight

• 26d

  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

  26d

  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

  26d

  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

  26d

  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

• 27d

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

  Montréal, QC

  

  Electronic Arts

  8+ YOECandidates need 8+ years of engineering experience, including 4+ years running ML systems in production. Strong Python, framework-level PyTorch and inference server skills (vLLM, SGLang or TensorRT-LLM), and experience with distributed data processing and AWS ML infrastructure are required.

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

• 27d

  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

• 29d

  Principal AI Cloud Engineer

  Toronto, ON

  Full Time

  

  Bank of Montreal

  7+ YOECandidates need a degree in computer science or engineering, 7+ years building large cloud systems and 5+ years on Azure or AWS. They need strong hands-on skills in Kubernetes, infrastructure-as-code, GPU clusters, MLOps and LLMOps, plus Python and Go or TypeScript.

  Kubernetes, Terraform, Bicep, Azure, AWS, Prometheus

• 29d

  Developer Relations Manager, Higher Education and Research - Foundational AI

  Toronto, ON

  Full Time

  NC

  NVIDIA Canada Dev. Inc.

  8+ YOECandidates need a PhD or equivalent research depth in a technical field and 8+ years of experience. They need deep expertise in foundational AI, hands-on skills with PyTorch, JAX and GPU workflows, and published or open-source research credibility.

  PyTorch, JAX, CUDA, TensorRT-LLM, Triton Inference Server, NeMo

• 29d

  Staff Machine Learning Engineer

  Toronto, ON

  

  OpenTable

  7+ YOECandidates need 7+ years of software engineering experience, with substantial time building and operating ML systems in production. They need strong Python, a typed language such as Java, hands-on cloud model-serving experience, and MLOps and technical leadership skills.

  Spark, Airflow, SageMaker, Snowflake, PyTorch, Docker

• 29d

  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

• 29d

  Staff AI Platform Engineer - Inference & Agentic Systems

  Toronto, ON

  HybridFull Time

  P

  Paytm

  8+ YOECandidates need 8+ years of software engineering experience, including 3+ years in AI systems or LLM applications. They need strong distributed systems skills, production LLM evaluation experience, and proficiency in TypeScript or Python.

  Temporal, Kubernetes, Bun, vLLM, TensorRT-LLM, Triton

  29d

  Senior AI Engineer

  Toronto, ON

  HybridFull Time

  P

  Paytm

  5+ YOECandidates need 5+ years of software engineering experience, including 3+ years in AI systems or LLM applications with production systems shipped end-to-end. They need strong Python, production experience on AWS and Azure with Docker and Kubernetes, knowledge of agentic security risks, and strong communication skills.

  Python, Docker, Kubernetes, AWS, Azure

• 29d

  Software Engineer II — Agentic AI Foundations

  Toronto, ON

  $135k–$175k/yrOn-siteFull Time

  

  Socure: The leading provider of digital identity verification and fraud solutions.

  2+ YOECandidates need a CS or related degree, or equivalent practical experience, plus 2+ years of professional software engineering. Strong knowledge of LLMs, agentic AI, GPU model serving, distributed systems and a modern backend language is required.

  CUDA, vLLM, Ollama, LLMLite, TensorRT-LLM, Triton Inference Server

17 companies