Highlights
- Pro
Block or report aryanputta
Block user
Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.
You must be logged in to block users.
Close all issues, pull requests, and discussions opened by this user
Content in all repositories owned by your account will be closed.
Add an optional note
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abuse
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
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
OPEN SOURCE
38 merged pull requests across NVIDIA · IBM · Dynamo · FlashAttention · Kubernetes · Microsoft · simdutf · apache · ArduPilot · AWS · EleutherAI · HuggingFace · kornia · Liger Kernel · Pulumi — 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 |
SYSTEMS WORK
|
KVCacheForge-X KV-cache bottleneck lab. Measures TTFT, latency, throughput, HBM stalls, and GPU busy against baseline deltas. |
RoboFleetOps AWS-native robotics fleet control plane on Lambda, DynamoDB, SQS, IoT Core, and API Gateway, deployed via CDK CI. |
|
PosCacheBench Long-context benchmark for positional-attention failure modes under fixed KV-cache budgets. |
LunarLinkBench Monte Carlo model of lunar comms links, separating relay passes from direct-to-Earth feasibility. |
RESEARCH
|
satellite telemetry anomaly detection 100K telemetry readings · 5 NASA/ESA fault modes · recurrence-plot CV · 0.91 F1 on Kepler-class wheel oscillation PDF · repo |
bell labs ml impact analysis 71-paper corpus · semantic clustering · co-authorship networks · Gradient Boosting AUC 0.674 · SHAP attribution PDF · repo |
How I work: every performance claim ships with reproducible commands, a named baseline, the hardware and software environment, and an honest limitations section. A result I cannot reproduce is not a result.
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
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
Pinned Loading
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.