Experience

• Distributed inference system using disaggregated serving, speculative decoding, and KV cache quantization — 4× throughput, latency <1 s vs vLLM baseline (5+ patents pending).
• RL-based quantization framework for Post-Training Quantization — 2.6× compression with minimal perplexity loss.
• Diffusion-based generative stability for automated fact verification (accepted FEVER @ EACL 2026).
• Theory of mind distillation via sequential SFT and preference-based refinement (accepted AAAI ToM 2026).
• Mamba-based reranker to mitigate adversarial attacks in RAG systems (ongoing).

• Built CogniSQL-R1-Zero — Text-to-SQL reasoning model via GRPO RL and DeepSpeed across 4× A100 GPUs. SOTA on BIRD benchmark, outperforming 236B+ models (arXiv).
• Agentic framework with self-healing, test-time scaling, and CoT reasoning — 30% accuracy gain; Copilot now in production.

Real-time theft detection using SlowFast networks and 3D CNNs, optimized for low-latency edge deployment.

Researched and implemented two features for the DocX Document AI product. Used SonarQube for code quality analysis.

AI/ML work on drone footage (120m altitude). Led mentoring group guiding 30+ interns.

Developed two end-to-end ML projects (Omnizenon & KnowCrimez). Applied ML for data analysis and deployed web UIs.

Abstractive text summarization using HuggingFace Transformers. Benchmarked accuracy across LLMs.

Sprint tickets, model building, API implementation, and database maintenance.

• Hybrid CNN+GRU+LSTM for lymphoma detection from histopathology images — Dr. Vivek Bhardwaj (accepted ICCCNT @ IIT Indore 2025, oral).
• Hybrid sentiment classifier: transformer embeddings + attention-driven recurrence + numerical fusion — Dr. Jayesh Gangrade (submitted Discover Computing).
• Real-time QUIC traffic classifier with LightGBM and SHAP+LIME explainability — Mr. Rajesh Kumar (accepted ICCCNT @ IIT Indore 2025).

RL (TD3)-based autonomous navigation for robots in nuclear radiation environments — Ushnish Sarkar (Scientific Officer F).

Hyperspectral image classification on the QUH dataset (10⁶+ samples) — Prof. Rajeev Srivastava. Hybrid deep learning model achieving 91.90% accuracy.

B.Tech. (Hons) CSE — Specialization: AI & ML · GPA 8.56/10
Dean's List 7× · 4× Student Excellence Award · MUJ Wizard Programmer Gold Medal · Tea with President Award

Led workshops at IBM Z Datathon guiding 3300+ students in LinuxONE for AI development. Mentored winning teams on mainframe-based ML integration.

Tutorials and lab sessions for AI3241 Reinforcement Learning and AI3231 Computer Vision & Pattern Lab.

300+ members in first year. Organized events and hackathons on ML, CV, and NLP.

Speaker at IBM Z Day. Promoting mainframe technology globally.

One of 10 leaders among 216 ambassadors globally. Works with the Streamlit team directly.