AI is growing faster than any technology in history and the explosion in demand has created a massive infrastructure gap; we can no longer build chips or power stations fast enough to keep up. The industry is still leaning on a ten-year-old hardware blueprint that has reached its limit. A new paradigm that is faster and more efficient will be the biggest economic opportunity of the next century and create the most important company of the next decade. The OLIX Decode Accelerator 1 (DX-1) is the first accelerator architected specifically for decode. Rack-scale co-design of logic, data movement, packaging, optics and interconnect enables a step change in system level performance.
We're searching for a Software Engineering Intern to join the Toronto team building the software stack (compiler, runtime, simulation and tooling) for our next-generation Accelerator. DX-1 is a dataflow architecture built specifically for decode, deployed in a disaggregated inference environment.
Contract Duration: 4-month term, extendable to 8-months.
Level Intern / Co-op
Project Ownership: Own and deliver scoped projects on your team’s roadmap, with a named mentor and a defined outcome by the end of your term.
Build and Ship: Contribute production code to our compiler, runtime, simulation or developer tooling, to the same standard as the rest of the team.
Optimize Performance: Apply techniques such as layout, scheduling and tiling, or extend our simulation so that it models real system behaviour more faithfully.
Partner Across Teams: Work directly with compiler, systems, FPGA and ASIC engineers to understand device trade-offs and where your work fits.
Measure and Communicate: Ground conclusions in measurement rather than assumption, and report results clearly.
Working toward a Bachelor’s or Master’s degree in computer science, computer engineering, electrical engineering, mathematics, or a related field, with an available co-op or internship term.
Practical experience with C/C++ programming beyond coursework.
Solid systems fundamentals, including memory hierarchies, concurrency, and performance analysis.
Demonstrated depth in either compilers or systems software.
Familiarity with ML framework internals, low-level programming, or optimisation techniques.
Strong problem-solving skills and the ability to think critically and creatively.
Excellent teamwork and communication skills, with the ability to collaborate effectively with cross-functional teams.
Exposure to LLVM, OpenXLA/XLA, MLIR or TVM
Familiarity with how LLM inference runs in practice (KV cache, prefill and decode, batching, quantisation)
Experience with non-GPU hardware, including FPGA work, simulation, emulation or bring-up
PyTorch or JAX internals beyond the user-facing API
Competitive Salary: $60/hour CAD for the internship term.
Elite Hardware: M4 Macs come as standard, with M4 Pro upgrades for our engineering team. We will provide whatever you need to do your best work.
Optimal Environment: High-spec noise-cancelling headphones and a fully ergonomic workstation designed for deep focus.
Based in our Toronto office, alongside the engineers you will be working with.
Caffeine on Us: We’ve got you covered with a tab at our favourite local coffee shop.
Due to U.S. export control regulations, candidates’ eligibility to work at OLIX depends on their most recent citizenship or permanent residency status. We are generally unable to consider applicants whose most recent citizenship or permanent residence is in certain restricted countries (currently including Iran, North Korea, Syria, Cuba, Russia, Belarus, China, Hong Kong, Macau, and Venezuela). Applicants who have subsequently obtained citizenship or permanent residency in another country not subject to these restrictions may still be eligible.
The latest generation of AI models achieve breakthrough performance by using vastly more tokens to solve complex problems. As frontier models become more sophisticated, demand is compounding faster than today’s infrastructure can scale.
Even the most dominant players, with full-stack control across silicon, software, and supply chains, are unable to solve this within the existing architecture. Inherent constraints in physical design and packaging mean a GPU-based approach is incapable of simultaneously delivering high throughput and high interactivity at low cost. Continuing AI’s advance and making it available to everyone requires a new compute paradigm. One that can overcome the fundamental limits of memory, energy, and speed that define today’s systems.
If you like working on difficult and consequential problems, we want you at OLIX. We have offices in London, Austin, Toronto, and Bristol.
Check out our careers page at olix.com/careers
