Experience
Supervised Program for Alignment Research (SPAR)
Research Mentee · Mentored by Sriram Balasubramanian (UMD, College Park) · February 2026 – May 2026
Working on Automated Circuit Analysis for Real-time Internal Monitoring.
- Building automated agents for analyzing large and complex attribution graphs from neural networks.
- Fully authored the task based on finding spurious correlation for validating the system and detecting failure modes.
- Extending the system over more realistic tasks like secret knowledge elicitation and misreporting tool calls.
UCR NLP Lab
Research Intern · Advised by Prof. Yue Dong · January 2025 – December 2025
Working on methods to combine interpretability tools with fairness diagnostics from social science to design interventions that target emergent activation circuits in LLMs responsible for particular behavioral tendencies.
- Understanding LLMs’ response instability over longer context and prompt manipulation.
- Using mech-interp to understand LLMs behavior over subjective domains e.g., socio-political reasoning.
- LLMs’ social epistemology using Bayesian statistics to model belief depth and opinion dynamics in LLMs.
Limited
AI Research & Engineering · September 2020 – Present
R&D (Sep 2020 – Jun 2021) → AI SWE (Jul 2021 – Dec 2023) → Lead AI Research Engineer (Jan 2024 – 2026)
I led a team of six research engineers developing production-grade NLP and computer vision systems deployed across multiple industrial domains. Key projects I directed include:
- Exercise Monitoring System for LG Nova, which used multimodal pose-estimation and language models to provide real-time feedback on workout form.
- Resume Shortlister, a RAG-based ranking engine that matched requirements from RFPs or job descriptions with candidate resumes using a hybrid approach combining rule-based filtering with semantic retrieval.
- Drawing Checker, a vision system to automate design-error detection in engineering drawings through deep-learning-based object detection and geometric analysis.
Pvt. Limited
NLP and Data Scientist · Part Time · August 2021 – November 2024
Extracting data-driven insights from medical data of Bangladesh and developing a smart healthcare platform that uses AI to deliver personalised healthcare services in local languages. Major contributions:
- Empowering mental health support for Bengali speakers through a conversational AI chatbot.
- Synthetic patient generator reflecting local demography.
- Classifier for clustering patient disease using symptoms and other demography.
- Training and serving of a voice-based patient symptom collector.
- Design and development of an audio data collection portal.
GRP, ICT Division
DevOps Engineer · May 2019 – August 2020
Automating the deployment and monitoring of numerous microservices. Major contributions:
- Automation scripts for deploying web apps and micro-services in Docker.
- Gateway configuration using NGINX reverse proxy.
- Document generation scripts from Google Sheets.
Skills
Programming Languages: Python · Java · Shell · JavaScript · Scala · C · C++ · LaTeX · SQL · TypeQL · Assembly
Libraries: Pandas · Datasets · ScikitLearn · OpenCV · Transformers · SpaCy · PyTorch · SQLAlchemy · TensorFlow · SocketIO · OpenGL · CTranslate2
Model Experience: LLaMA · Adapters · LoRA · QLoRA · DIET · BERT · DeepSpeech · Whisper · YOLOv5
Frameworks: LangChain · RASA · Flask · FastAPI · Spark · PySpark · OpenWhisk · PyQT
Tools & Services: Jupyter · Colab · Git · Huggingface · Maven · NGINX · Keycloak · Docker · Kubernetes · Ansible · AWS (EC2, Lambda, Cognito) · Grafana · PostgreSQL · TypeDB