AI infrastructure · LLM inference · KV cache systems · distributed systems · cloud backends
_{Rutgers computer science and data science student. I work on inference latency, memory bandwidth, and throughput under real hardware constraints, and I contribute those fixes upstream.
portfolio · merged open-source PRs · LinkedIn}

_{45 merged pull requests across NVIDIA · MLH-Fellowship · torch-spyre · Dynamo · FlashAttention · Kubernetes · Microsoft · simdutf · apache · ArduPilot · AWS · EleutherAI · HuggingFace · kornia · Liger Kernel · NVlabs · Pulumi · watertap-org — inference, CUDA, CI, and ML-systems internals}

NVIDIA/cuda-python#2087 FIPS-safe hashes for program cache keys	NVIDIA/cuda-quantum#4688 nvqpp: discriminate measured-register bool iteration
huggingface/accelerate#4054 Aggregate profiler memory example	Dao-AILab/flash-attention#2622 weights_only=True across all torch.load sites
ai-dynamo/dynamo#10281 HTTP 415 for unsupported image formats	linkedin/Liger-Kernel#1157 Guard save_for_backward on grad_bias in fused linear CE

_{→ all merged pull requests}

_{Available for software engineering, research engineering, systems engineering, and machine learning internships and co-ops, including off-cycle terms. Also AI infrastructure and ML systems roles, cloud and backend engineering, early member-of-technical-staff (MTS) programs, and founding or early-stage engineering at seed and Series A startups.
Undergraduate at Rutgers University, B.S. Computer Science and Data Science, class of 2028. Based in the New York and New Jersey area, open to relocation including San Francisco and the Bay Area, and to remote.
systems project evidence · KV-cache writing · aryanputta.com}