Leads the team this role joins
Heads the group this role sits in
In-house, owns the opening
From your own Gmail and LinkedIn.
About the role
This is a full-time lead or senior inference engineering role for candidates based in Canada, listed on behalf of a partner company through Jobgether. The engineer builds and runs the production serving platform for large language models, with a focus on latency, reliability and cost. It suits senior infrastructure engineers with Kubernetes and LLM serving experience who can help set up a newly formed team.
What you’ll do
- Build, run and maintain production model-serving infrastructure.
- Apply batching, caching and quantisation to reduce latency and operating cost.
- Improve observability, monitoring and operational visibility.
- Build the controls and evidence needed for an ISO 27001 compliance path.
- Set up cost tracking and GPU capacity contingency plans.
- Integrate new model releases with training and evaluation teams.
- Establish on-call, incident review and operational documentation practices.
What they’re looking for
- Hands-on infrastructure experience with Kubernetes or similar, owning production systems
- Experience operating model services at peak traffic, including scaling and disaster recovery
- Model-serving or LLM inference optimisation experience at scale
- Background in large distributed systems focused on availability and reliability
- Proven ability to resolve production incidents under real traffic
- End-to-end software delivery from design through operations
- Autonomy, technical judgement and the ability to mentor
Nice to have
- vLLM, TensorRT-LLM, Triton or SGLang experience
- GPU cluster capacity planning, or multi-region or multi-cloud deployments
- Experience in regulated settings such as ISO 27001 or SOC 2
- Rust or Go
- Systems-level performance tuning across networking, hardware and software
What’s on offer
- CAD 140,000 to 175,000 annual base salary for Ontario, Canada
- Possible annual performance bonus
- Retirement savings, flexible vacation and incentive programmes
- Working from anywhere for up to eight weeks per year
- Two company mental health days per year and Headspace access
- Tuition reimbursement and skills development
- Two paid volunteer days per year
Skills
Questions about this role
How much does it pay?
The base salary is CAD 140,000 to 175,000 per year for Ontario, Canada, with a possible annual bonus.
Is this role remote?
The role is listed as remote, with flexible arrangements including working from anywhere for up to eight weeks a year.
Is Kubernetes experience required?
Yes, hands-on infrastructure experience with Kubernetes or comparable technologies is required.