Sr. SDE, Edge AI ML Platform – Amazon – Vancouver, BC

Amazon Devices (Lab126) is building the future of on-device AI — and the Edge AI ML Platform and Infrastructure team in Vancouver, BC is at the centre of it. They’re looking for a Senior Software Development Engineer to lead the architecture and delivery of a platform that enables teams across Amazon to train, optimize, evaluate, and deploy generative AI models on devices and in the cloud.

This isn’t a role where you’ll be maintaining someone else’s system — you’ll be shaping a self-service ML workflow platform that handles large language, vision, audio, multimodal, and mixture-of-experts models. You’ll combine deep hands-on engineering with technical leadership, working alongside applied scientists, GPU kernel engineers, compiler teams, and hardware teams to solve genuinely hard problems at scale.

About the Role: Sr. SDE, Edge AI ML Platform

The Edge AI ML Platform team owns the end-to-end foundations that connect model development to deployment. Today, optimizing a large model for a new hardware target requires experts to stitch together multiple systems by hand. Your job is to turn that into a repeatable, scalable, self-service workflow. You’ll lead architecture decisions, write and review code, and drive cross-team programs — all while keeping one eye on long-term platform integrity and the other on measurable, incremental delivery.

Collaboration is central to this role. You’ll work closely with applied scientists, ML engineers, compiler and runtime teams, hardware teams, and product teams to clarify ambiguous requirements and deliver reliable systems for models with hundreds of billions of parameters. You’ll also mentor engineers, elevate code and design review practices, and help build a strong engineering team right here in Vancouver.

Benefits and Salary

The base salary range for this position in Vancouver, BC is $150,700 to $251,700 CAD annually. Amazon’s total compensation package may also include sign-on payments and Restricted Stock Units (RSUs). Benefits include health insurance (medical, dental, vision, prescription, basic life and AD&D), a Registered Retirement Savings Plan (RRSP), a Deferred Profit Sharing Plan (DPSP), paid time off, and additional resources to support health and well-being.

Responsibilities

As a Senior SDE on the Edge AI ML Platform team, your day will shift between architecture and implementation. You’ll review designs for model onboarding interfaces, investigate failures in distributed training runs, profile GPU workloads alongside scientists, and lead cross-team reviews of end-to-end deployment paths. These responsibilities are critical to keeping Amazon’s model development pipeline reliable and efficient at scale.

• Lead design and delivery of distributed ML platform services across model ingestion, optimization, training, evaluation, packaging, and deployment
• Define stable APIs and architecture boundaries that let scientists add algorithms without coupling research code to infrastructure or deployment implementations
• Design distributed training capabilities across data, tensor, pipeline, and model parallelism for large language and multimodal models
• Scale GPU cluster workflows while improving training throughput, memory efficiency, communication performance, failure recovery, and developer iteration time
• Develop infrastructure connecting distributed training with distillation, quantization, pruning, and other model optimization techniques
• Build evaluation and artifact workflows that measure model quality and system performance, then carry validated models through hardware deployment
• Establish CI/CD, automated validation, regression testing, observability, and release mechanisms for GPU-intensive ML workloads
• Profile and optimize end-to-end system performance with applied scientists and GPU kernel engineers, translating bottlenecks into durable platform improvements
• Mentor engineers, improve code and design review practices, and support recruitment and team development in Vancouver

Requirements / Skills

Amazon is looking for a senior engineer who is equally comfortable writing production code and leading multi-team technical programs. The ideal candidate has deep experience with distributed systems and ML infrastructure, and knows how to build platforms that scientists and engineers actually want to use. Strong communication and the ability to navigate ambiguous, high-stakes technical decisions are essential.

• 5+ years of professional software development experience outside of internships, with strong proficiency in at least one programming language
• 5+ years of experience leading architecture or design of new and existing systems, including design patterns, reliability, and scaling
• Experience with distributed systems or high-performance computing — this is a core requirement, not a nice-to-have
• Technical leadership experience as a mentor, tech lead, or engineering team lead
• Experience with ML training or inference platforms using frameworks such as PyTorch, TensorFlow, JAX, NeMo, or Megatron (preferred)
• Familiarity with containers, Kubernetes, AWS, CI/CD, and production operations (preferred)
• Experience with model compression, quantization, knowledge distillation, or edge deployment (preferred)

How to Apply

To apply, visit the official Amazon job posting using the link below. Make sure your resume is up to date and reflects your experience with distributed systems, ML infrastructure, and technical leadership before submitting.

Share This Opportunity

Know someone who might be interested? Share this job posting and help them join Amazon in Vancouver.