I write C++ and CUDA for LLM inference. 2 CUDA PRs merged into llama.cpp; now working on block-FP8 GEMM support for Ada GPUs (L4/L40S/4090) in vLLM. Built verbum.cpp, an inference engine from scratch that matches HuggingFace to 3e-5.
Looking for inference / ML performance / CUDA roles at AI startups: remote, full-time or long-term contract, with flexible hours for US or EU overlap. Available for interviews from December 2026.
Remote: Yes
Willing to relocate: No
Technologies: C++20, CUDA, CUTLASS, Triton, Python, PyTorch, vLLM, llama.cpp/ggml, FP8/INT8 quantization, Linux
Résumé/CV: https://aman-portfolio-rho-six.vercel.app/resume.pdf
Email: [email protected]
I write C++ and CUDA for LLM inference. 2 CUDA PRs merged into llama.cpp; now working on block-FP8 GEMM support for Ada GPUs (L4/L40S/4090) in vLLM. Built verbum.cpp, an inference engine from scratch that matches HuggingFace to 3e-5. Looking for inference / ML performance / CUDA roles at AI startups: remote, full-time or long-term contract, with flexible hours for US or EU overlap. Available for interviews from December 2026.
Portfolio: https://aman-portfolio-rho-six.vercel.app
GitHub: https://github.com/amankarki151