Location: Canada (Remote / Hybrid options available)

Language: English, advanced written and verbal communication required

Compensation: open

 

About the Opportunity

This is a hands-on senior opportunity for a AI & LLM Engineer who thrives on making large language models work efficiently in the real world. The focus is firmly on inference performance, latency, and memory optimization, particularly in environments where hardware constraints demand creative and practical solutions.

You’ll work closely with infrastructure, hardware, and product teams to deploy and optimize LLMs across non-traditional and edge environments, where every millisecond and megabyte matters.

 

What’s in it for You

You’ll join a workplace that values curiosity, collaboration, and thoughtful problem-solving, where technical depth is respected and ideas are openly shared. You’ll work closely with senior technical leaders who are committed to mentorship, knowledge exchange, and helping their teams grow.

This is an environment where you can expand your influence by shaping systems that move from experimentation into real-world use.

 

Your Responsibilities

• You’ll design, optimize, and deploy LLM inference pipelines with a strong focus on latency, throughput, and memory efficiency.
• In this role, you’ll tune models for performance across constrained and non-datacenter hardware, including edge GPUs and custom accelerators.
• You’ll work hands-on with low-level PyTorch, inference runtimes, and quantization techniques to push system performance forward.
• You’ll collaborate across hardware and software teams to identify and resolve production bottlenecks.

 

Skills and Qualifications

• 5+ years of hands on experience working with large neural networks in production environments.
• Proven experience with large language models ranging from billions to over 100B parameters.
• Strong understanding of transformer architectures, attention mechanisms, and KV cache behavior.
• Practical experience with PyTorch beyond high-level APIs, model quantization, and inference runtimes such as TensorRT or ONNX Runtime.
• A systems-oriented mindset with experience working across hardware and software boundaries.

 

Note from the Hiring Manager

“We’re looking for someone who has truly been in the weeds, shipping and optimizing LLM systems, and who enjoys solving hard performance problems alongside a highly collaborative team.”

 

Why Partner with Altis

If you’ve never worked with a staffing agency before, don’t worry, we make it easy. You’ll still engage directly with the client while we handle the logistics, provide guidance, and keep you informed every step of the way. We’ll represent your strengths, guide you through each stage of the process, and ensure the experience feels personal and transparent.

We appreciate the time and effort all applicants invest in their submissions. Please note that only candidates shortlisted for this role will be contacted directly. However, your profile will remain under consideration for future opportunities that align with your experience and career goals. All qualified applicants will receive fair consideration for employment. We welcome individuals of all backgrounds, experiences, and identities including those who identify as women, members of racialized groups, Indigenous Peoples, persons with disabilities, and 2SLGBTQIA+ communities. If you require an accommodation, please review our accessibility policy and reach out to our accessibility officer with any questions. Our human recruiters review all applications and always make the final hiring decision. On occasion, we also use AI-assisted tools to help review applications.