Hi, I'm Saketh. A student and passionate photographer!
Hi, I'm Sai Saketh Cherukuri, an M.Sc. Mathematics student specializing in Computer Science at Sri Sathya Sai Institute of Higher Learning. I work on machine learning systems, with an emphasis on inference performance, GPU profiling, deployment, and model efficiency.
My recent projects include an MLPerf Inference study of Llama 3.1 8B, an H200 quantization benchmark suite, and a periocular age and gender recognition system. I use tools such as vLLM, PyTorch, MLflow, Nsight Systems, and Nsight Compute to turn performance questions into reproducible experiments.
M.Sc. Mathematics, Computer Science specialization, 2024 to 2026
B.Sc. Mathematics, Honours, 2020 to 2023
Selected Work
Projects spanning machine learning, deep learning, LLM inference, GPU profiling, developer tooling, and systems programming.
A reproducible H200 benchmark harness that pairs vLLM throughput experiments with ROUGE validation and Nsight trace analysis.
Benchmarks AWQ, GPTQ, FP8, BF16, and NVFP4 variants on H200 MIG across throughput, TTFT, TPOT, and published accuracy tasks.
A refreshed periocular pipeline with subject safe gender evaluation, strict eye region age crops, and custom PyTorch model comparisons.
A Java toolkit that scans C++, CUDA, and Python source, dispatches language specific checks, and presents reports through JavaFX.
Implemented a compact two pass SIC/XE assembler in C++ that builds a symbol table, resolves directives, and emits standard object program records.
Built a recursive descent parser in C for a simplified Pascal like language, validating declarations, assignments, expressions, and basic control flow syntax from token streams.
Email me at ssaketh.2002@gmail.com. I am based in Maryland and authorized to work in the United States without sponsorship.