Sr. Engineer, Kernel Development and Optimization
Tenstorrent7 months ago
Belgrade, SerbiaSenior / Mid Level
Responsibilities
- Design, implement, and optimize GPU-style kernels such as matrix multiplication and attention primitives.
- Take ownership of performance by identifying bottlenecks and delivering measurable throughput improvements.
- Contribute to host-side orchestration code and parallelization strategies.
- Develop micro-benchmarks, regression tests, and tooling to ensure correctness and sustained performance gains.
- Collaborate with compiler, runtime, ML, and hardware teams to integrate kernels into production systems.
Requirements
- Strong C++ systems engineering experience with performance-critical or low-level software.
- Ability to reason about concurrency, synchronization, and compute versus memory trade-offs.
- Data-driven approach using profiling and benchmarking for optimization decisions.
- Effective debugging skills for complex runtime or kernel-level issues in large codebases.
- Structured thinking to break down ambiguous performance problems into measurable experiments.
Benefits
- Highly competitive compensation package.
- Equal opportunity employer.
About Tenstorrent
Tenstorrent builds AI compute hardware and RISC‑V CPU technology for companies developing training and inference workloads in data centers and at the edge. The business sells accelerator cards and systems with a full software stack, and licenses RISC‑V CPU IP. Founded in 2016 and headquartered in Toronto, it is privately held and led by semiconductor architect Jim Keller.