Software · Data · Machine Learning
Tempe, Arizona
MS Data Science student at Arizona State University.
From storage internals to evaluated AI, I care about
how systems work and where they break.
Selected work
Six projects across systems, data, and applied ML.
A Go key-value database that connects an embedded LSM storage engine to a Raft-replicated cluster.
Make the durability boundary explicit: the embedded WAL and replicated Raft log serve different modes.
Quorum writes. Recoverable state.
Synthetic-data case studies
Three connected studies in causal inference, inventory forecasting, and churn prediction, built on one synthetic e-commerce dataset.
Evaluate against meaningful baselines and distinguish a statistically significant result from a promising direction.
Three studies. One synthetic dataset.
A reproducible comparison of vLLM serving configurations and a serial HuggingFace baseline on the same GPU and workload.
Audit the baseline and quantization kernels before attributing performance differences to the serving engine.
Throughput, latency, memory, and cost.
A Go feature store with historical training joins, Parquet offline storage, and Redis online serving.
Only join features available at the prediction timestamp, within their validity window.
Point-in-time correctness by design.
ML experiment
A controlled comparison of LoRA, DoRA, and IA3 against zero-shot and few-shot math-reasoning baselines.
Keep the model, data budget, and evaluation consistent, and publish negative results.
The baseline beat every adapter.
An internal knowledge assistant with department-scoped retrieval, hybrid search, streaming responses, and evaluation.
Enforce department permissions in retrieval, alongside authentication and output handling.
Access control belongs in retrieval.
About
I’m Aditya, an MS student in Data Science, Analytics, and Engineering at Arizona State University. My work connects software engineering with applied machine learning: from database internals and model serving to experimentation and retrieval systems.
I enjoy the parts that make a system trustworthy: recovery after a failure, features that don’t leak future data, and evaluations that reveal where a model falls short. I’m exploring Software Engineer, Data Scientist, Machine Learning Engineer, and AI Engineer opportunities.
Away from the keyboard, I follow tennis and chess. I also built a chess tutor to explore how retrieval and structured reasoning can support a subject I enjoy.
Experience
– Present
Open source
Contributions to database and AI tooling, with a focus on correctness and regression coverage.
–
LetsGrowMore
Developed image-based ML applications and full-stack web projects.
–
BSNL LTD
Worked on diagnostics and troubleshooting for telecom network infrastructure.
Technical toolkit
Tools and methods used across my projects and experience.
Education
Graduate studies
MS - Data Science, Analytics, and Engineering
Data Mining · Data Processing at Scale · Natural Language Processing · Statistics
Undergraduate studies
Bachelor of Technology - Electronics and Communication Engineering
Data Structures · Algorithms · Operating Systems · DBMS · Computer Networks
06 / Keep exploring
Voice agents, retrieval systems, graph analytics, and computer vision.
Recent activity
GitHub snapshot updated . Refreshed weekly.
08 / Get in touch
Exploring opportunities across software engineering,
data science, machine learning, and AI.