I'm interested in pushing the limits of real-time high-quality graphics, and have used GPUs and other specialized processors for computation, and have written very fast ray tracers using GPUs (pre OptiX and RTX).

I have a fairly strong optimization background in general, and I have extensive knowledge of ray tracing and global illumination.

I am very interested in massively parallel programming problems, especially on the small scale (SIMD/MIMD), but also including instruction level and task level parallelism. I have written SIMD code for SSE# chips, and with NVIDIA's CUDA language. I have also used pthreads, boost threads, MPI, Google-internal threading libraries, std::thread and std::atomics.