Carnegie Mellon University
M.S. in Computational Data Science
Coursework includes Search Engines, Large Language Models Applications, Cloud Computing, and Machine Learning Systems.
CMU · Carnegie Mellon University · M.S. Computational Data Science
Sai Gopal Reddy Kovvuri
I build agentic AI and machine learning systems spanning LLM orchestration, inference, compilers, information retrieval, and distributed infrastructure.
About
Researcher and engineer at the intersection of ML and systems.
I am Sai Gopal Reddy Kovvuri, a Master's student in Computational Data Science at Carnegie Mellon University (CMU), and an AI Engineer Intern at Klaviyo. I work on agentic orchestration for conversational marketing analytics using LangGraph, LLM tool calling, specialist-agent workflows, and evaluation pipelines.
Previously, I built compiler and inference components across Apache TVM, MLC-LLM, WebLLM, and FlashInfer-Bench at CMU's Catalyst Group, and production payment systems and RAG-based developer tooling at Juspay. I completed my B.Tech in Computer Science at Shiv Nadar University with high distinction, and my research has appeared at BMVC and NCC.
Education
Academic Background
Shiv Nadar University
B.Tech in Computer Science
Graduated with CGPA 9.12/10, high distinction, and four Dean's List honors.
Experience
Research and Engineering
Jun 2026 - Aug 2026
AI Engineer Intern, Klaviyo
- Engineered ReAct-style agentic orchestration with LangGraph, LLM tool calling, and specialist-agent workflows to deliver conversational marketing analytics across 4,000+ beta accounts.
- Built Braintrust-based evaluation pipelines to validate and improve the agent's end-to-end behavior.
Feb 2026 - Apr 2026
Research Assistant, Catalyst Group
- Built compiler and inference components across Apache TVM, MLC-LLM, and WebLLM to improve deployment performance and device compatibility.
- Extended FlashInfer-Bench for newer model architectures and real SGLang inference workloads, improving benchmarking coverage.
- Built FP16 GEMM kernels for NVIDIA Blackwell GPUs using TVM/TIRX, implementing tiling, asynchronous loads, pipelining, warp specialization, and cluster optimizations.
Dec 2023 - Jul 2025
Software Engineer, Juspay Technologies
- Built CodeGen, an internal RAG-based developer tool that grounded LLMs in the codebase and automated 28% of payment gateway integration work.
- Integrated six payment gateways into the payment orchestrator, maintaining critical payment logic and encryption workflows.
- Used Kibana and structured logging to analyze transaction logs and surface Redis cache performance issues per API flow.
Jul 2023 - Aug 2023
Data Science Intern, Code for GovTech 2023
- Built an on-demand data generation and fine-tuning pipeline for Hugging Face models from natural-language user prompts.
- Applied Stanford NLP's Demonstrate-Search-Predict framework to improve responses for government scheme queries.
Work
Projects
CX Group, CMU · Feb 2026 - May 2026
Model-Based Approaches for Data-Effective Pretraining
Built an offline Common Crawl simulator with model-based quality scoring, seed curation, and Weights & Biases metrics aligned with production pretraining crawls.
Cloud Computing, CMU
Twitter Recommendation Engine
Architected a three-tier Go microservice with gRPC serving 1,000+ RPS, backed by Spark ETL, MySQL, and AWS infrastructure managed with Terraform, Helm, and Kubernetes.
Machine Learning Systems, CMU
Distributed Training Systems
Implemented 2D parallel training from scratch using MPI collectives and Megatron-style tensor parallel communication, with ZeRO Stage-3 parameter sharding.
Search Engines, CMU
QryEval
Built an end-to-end neural search and RAG engine using BM25, dense retrieval, BERT reranking, learning-to-rank, and pseudo-relevance feedback.
Publications
Peer-Reviewed Research
National Conference on Communications, 2025
Revisiting Subject-Action Relevance for Egocentric Activity Recognition
Reddy, K.S.G., Prabhakar, M., and Mukherjee, S. Dual-stream CNN-LSTM approach for egocentric activity recognition.
IEEE XploreBritish Machine Vision Conference, 2024
UnSeGArmaNet: Unsupervised Image Segmentation using Graph Neural Networks with Convolutional ARMA Filters
Reddy, K.S.G., Bodduluri, S., Adityaja, A.M., Shigwan, S., Kumar, N., and Mukherjee, S. Graph-neural unsupervised image segmentation with ARMA filters.
BMVC ProceedingsSkills
Technical Toolkit
Programming
Python, Go, C++
ML and Data
PyTorch, LangGraph, FastMCP, scikit-learn, Hugging Face, NumPy, Pandas, FastAPI, FAISS, vLLM
Systems and Cloud
AWS, Azure, GCP, Docker, Kubernetes, Terraform, Helm
Databases and Tools
MySQL, PostgreSQL, MongoDB, Redis, Git, Kibana
Contact