Find work in Canada.

550,580 jobs across our Canadian network. How we count

Jobs in Canada

25+ jobs

Email me new jobs Save this search

Added 29 mins ago
N
Growth Operations Manager
nesto
Toronto, ON
- Full-time
Added 29 mins ago
CH
Advisor
Covenant Health Canada
AB · Edmonton, AB
- Full-time
Added 29 mins ago
AF
Quality Assurance Analyst (18-month temp)
ATB Financial
Calgary, AB
- Temporary
Added 29 mins ago
CH
Lead
Covenant Health Canada
AB · Edmonton, AB
- Full-time
Are you an analytics professional with a passion for healthcare improvement? Covenant Health is currently recruiting for a Connect Care reporting lead who will work closely with other team…
Added 59 mins ago
I
Systems architect
iSteer
Toronto, ON
- Full-time
Added 59 mins ago
RM
Supervisor, Centralized Scheduling
Ross Memorial Hospital
Kawartha Lakes, ON · Lindsay, ON
- Full-time
Added 59 mins ago
M
AVP, AI
Manulife
Toronto, ON
- Full-time
Added 1 hour ago
S
School Psychologist, Complex Developmental Behavioural Conditions (CDBC) - BC Children’s Hospital & Sunny Hill Health Centre
Sanya’k̓ula
Vancouver, BC
- Temporary
Added 1 hour ago
G
Architecte en information commerciale / Business Information Architect
Genetec
Montreal, QC
- Full-time
Added 1 hour ago
UO
Sessional Lecturer: MUI1080H5 S - Economic Development Planning
University of Toronto - Woodsworth College
Toronto, ON · Greater Toronto Area, Canada
- Full-time
Added 1 hour ago
SC
UGC Marketing Manager
SORA Clothing
Canada
- Full-time
Added 1 hour ago
HT
Master Data Mgmt Analyst
Husky Technologies
Bolton, ON
- Full-time
Added 1 hour ago
HT
VP, Accounting & Controllership (Husky)
Husky Technologies
Bolton, ON
- Full-time
Leveraging technology, ERP capabilities, analytics, and automation to improve productivity and decision support across Finance.
Added 1 hour ago
HT
Financial Manager - PLM (Product Line Mgmt)
Husky Technologies
Bolton, ON
- Full-time
Added 1 hour ago
HT
Director, Finance (CSM)
Husky Technologies
Bolton, ON
- Full-time
Improve reporting automation and self-service analytics capabilities where possible.
Added 1 hour ago
HT
Applications Engineer
Husky Technologies
Bolton, ON
- Full-time
Apply a data-driven, first-principles approach, leveraging scientific modeling, experimentation, and advanced analytics to understand, predict, and optimize complex physical phenomena.
Added 1 hour ago
I
Systems architect
iSteer
Toronto, ON
- Full-time
Added 1 hour ago
GD
HR Analytics & Compensation Analyst
General Dynamics Land Systems–Canada
London, ON
- Full-time
We are seeking a detail-oriented, data-focused professional to support our compensation programs and broader HR analytics.
Added 1 hour ago
B
Tenant Services Coordinator
BGIS
Toronto, ON
- Full-time
Added 1 hour ago
AM
Director Digital Solutions & Business Growth
Arc Mercer
Barrie, ON
- Full-time
Scale purchased services using automation, technology, and data analytics.
Added 1 hour ago
NB
Senior Analyst Custody Client Services
National Bank of Canada
Montreal, QC
- Full-time
Added 1 hour ago
I
Partner Enablement Leader
Intuit
Toronto, ON
- Full-time
Added 1 hour ago
NB
Chief Data Engineering Developer
National Bank of Canada
Montreal, QC
- Full-time
A career as a Chief Data Engineering Developer on the Analytics and Data team at National Bank means acting as a data engineering expert. In this role, you will have a direct impact on how…
Added 1 hour ago
NB
Chier Developer Data Engineering
National Bank of Canada
Montreal, QC
- Full-time
Added 2 hours ago
AH
Health Info Mngt Professional I - Clinical Coding Specialist
Alberta Health Services
Calgary, AB · Greater Calgary Metropolitan Area
- Temporary

Aptino, Inc.

Senior Machine Learning Systems Engineer

Canada

Contract

Apply About employer

Applications open in a new tab.

Job details

Job type: Contract
Posting language: English
Posted: Oct 30, 2026

Original job description

We are looking for an experienced Senior Machine Learning Systems Engineer to optimize large language model (LLM) inference performance across AWS Trainium platforms, including Trainium2 and Trainium3.

The ideal candidate will have strong hands-on experience in Python, PyTorch, LLM inference frameworks, and accelerator performance optimization. This role focuses on improving inference latency, throughput, scalability, and cost efficiency for production-grade AI workloads.

Key Responsibilities:

Optimize LLM inference performance, focusing on decode latency, throughput, and serving costs.
Work with AWS Trainium2/Trainium3, AWS Neuron SDK, and vLLM on Neuron.
Implement and evaluate speculative decoding and Multi-Token Prediction (MTP) for Qwen-family models.
Profile, benchmark, and optimize production LLM workloads across GPU and Trainium platforms.
Optimize prefill/decode performance, continuous batching, KV-cache, and tensor/expert parallelism.
Support long-context inference workloads (100K+ tokens) and multi-chip scaling.
Work with advanced AI architectures, including Mixture of Experts (MoE) and State Space Models.
Develop benchmarking reports, technical documentation, implementation guides, and customer runbooks.
Collaborate with customer engineering teams to deliver measurable performance improvements.

Required Skills & Experience:

5+ years of experience in Machine Learning or Systems Engineering.
2+ years of hands-on experience with production LLM inference or serving.
Strong programming experience in Python and PyTorch.
Hands-on experience with LLM serving frameworks such as vLLM, TensorRT-LLM, SGLang, or Triton Inference Server.
Strong understanding of LLM inference concepts, including prefill, decode, continuous batching, and KV-cache management.
Experience with performance profiling, benchmarking, and accelerator workload optimization.
Knowledge of attention mechanisms, Mixture of Experts (MoE), tensor parallelism, and expert parallelism.
Strong analytical, problem-solving, and technical communication skills.

Preferred Qualifications:

Experience with AWS Trainium, Inferentia, AWS Neuron SDK, NxD Inference, or Neuron Kernel Interface (NKI).
Experience with speculative decoding, Medusa, EAGLE, or Multi-Token Prediction (MTP).
Kernel development experience using NKI, Triton, or CUDA.
Experience with Mamba, State Space Models, or large Mixture of Experts architectures.
Knowledge of FP8/INT8 quantization and model accuracy validation.
Previous experience in customer-facing engineering, consulting, or technical enablement.

Apply About employer

More about this job

Responsibilities

Optimize production LLM inference performance, latency, throughput, scalability, and cost across AWS Trainium and GPU platforms. Implement and benchmark inference techniques and architectures, support long-context and multi-chip workloads, and deliver technical documentation and measurable improvements with customer engineering teams.

Requirements

Requires 5+ years of machine learning or systems engineering experience, including 2+ years working hands-on with production LLM inference or serving. Candidates should have strong Python and PyTorch skills, experience with LLM serving frameworks and performance optimization, and knowledge of inference concepts, parallelism, attention, and MoE; Trainium, kernel development, quantization, and customer-facing experience are preferred.

Skills

Python
PyTorch
LLM Inference
vLLM
AWS Trainium
AWS Neuron SDK
Performance Profiling
Benchmarking
Continuous Batching
KV-Cache Management
Tensor Parallelism
Expert Parallelism
Mixture Of Experts
Speculative Decoding
Multi-Token Prediction
Accelerator Optimization

Visa sponsorship

Not detected in the job text

Keywords

Python
PyTorch
Large Language Models
LLM Inference
AWS Trainium2
AWS Trainium3
AWS Neuron SDK
vLLM
TensorRT-LLM
SGLang
Triton Inference Server
NxD Inference
Neuron Kernel Interface
Speculative Decoding
Multi-Token Prediction
Medusa
EAGLE
Prefill
Decode
Continuous Batching
KV-Cache
Tensor Parallelism
Expert Parallelism
Mixture Of Experts
State Space Models
Mamba
NKI
CUDA
FP8 Quantization
INT8 Quantization

Report this job