I build applied ML systems, then test whether they actually work.
MS in Computer Science at Arizona State University, graduating May 2027. I care most about the part of ML work that decides whether a result is real: baselines, held-out data, and honest error analysis. Looking for full-time applied AI/ML engineering roles.
A simulated 4-way intersection in SUMO, controlled three ways: a fixed timer, a rule-based adaptive controller, and a DQN agent. A separate YOLOv8 detector, fine-tuned on real traffic-camera footage, is the perception front end.
Result
The rule-based controller cut average wait 66–70% under light-to-moderate demand. The detector reached 0.907 mAP50 on clips it never saw in training.
What didn’t work
Five DQN versions never beat the rule-based controller overall. Throughput, fairness and switching cost traded off against each other under every reward I tried.
North–south greenQueued 0 NS, 0 EWThrough 0Avg wait 0.0sLive: a simplified version of the adaptive rule. Green ends when its queue clears and the other side is waiting.
Upload PDFs, Word files or text, build an embeddings index, then summarize the documents or chat with them. Every answer cites the chunks it was grounded in.
Result
End-to-end pipeline from ingestion to cited answers, served over FastAPI with a Streamlit UI. The LLM can be swapped between a local Hugging Face model and the OpenAI API.
What didn’t work
Retrieval quality has not been measured yet. Without a labeled question set, I can’t say how often the right chunk is retrieved.
Image classification API. ResNet fine-tuned on CIFAR-100, served over FastAPI with a Streamlit front end. About 79% top-1 and 96% top-5 accuracy. Code
Real-time face mask detection. MobileNetV2 classifier with OpenCV face detection on a live webcam feed. Code
Chess bot. Minimax search with alpha-beta pruning and adjustable depth, played in the browser through p5.js. Code
Experience
Jun – Dec 2024
Software Developer
PEOCIT Software Solutions, Pune, India
Built a stock-market portfolio management web application in C# and .NET, working directly with the client and a designer.
Integrated real-time market data from third-party APIs into the application.
May 2023 – May 2024
Data Analyst Intern
Poona Switchgears, Pune, India
Compiled and analyzed electrical and production data in Python for an industrial electrical-panel manufacturer.
Turned the analysis into reports that informed manufacturing efficiency and cost decisions.
Education
Aug 2025 – May 2027
M.S. Computer Science
Arizona State University, Tempe, Arizona
Coursework: Statistical Learning Theory, Data Mining, Data Visualization, Semantic Web Mining, Knowledge Representation and Reasoning, Software Verification and Testing.
Aug 2021 – May 2025
B.Tech Computer Science and Engineering, CGPA 8.36/10
MIT World Peace University, Pune, India
Published a CNN-based flower recognition paper in IJFMR. Media Club president. Taught mathematics to 8th and 9th graders as a volunteer at Khelghar, an NGO for underprivileged children.
Tools
ML
PyTorch, TensorFlow, stable-baselines3, Ultralytics YOLOv8, scikit-learn, Hugging Face Transformers, Sentence-Transformers
