3+years industry ML
2peer-reviewed papers
2+years teaching assistant
10K+docs/day OCR scale
Fall 2027PhD target cycle

Industry track

Built production AI systems across OCR/document intelligence, voice AI, retrieval systems, and large-scale crawling. Engineering decisions prioritize measurable outcomes: throughput, latency, cost, and reliability.

Best for: AI/ML engineering roles, research engineer roles, startup applied AI positions, and teams needing end-to-end ML ownership from experimentation to deployment.

Core signal: practical systems at scale (10K+ OCR docs/day, multimillion-site pipelines, real-time voice interactions) with quantifiable optimization and delivery impact.

Document: Industry CV (PDF) · source (TeX)

Academic track

Research direction

Document AI and OCR in low-resource language settings, with emphasis on robust methods, reproducible experimentation, and practical deployment constraints.

Evidence of preparation

Peer-reviewed publications (ACM, Springer), strong undergraduate academic record (CGPA 3.96/4.00), and teaching experience in core CS/AI courses.

PhD positioning

Targeting fully funded US PhD programs (Fall 2027) with interests spanning document understanding, multimodal learning, and evaluation-oriented ML systems.

Work experience

  1. Senior Machine Learning Engineer

    Apurba Technologies Ltd. On-site · Dhaka, Bangladesh · Sep 2025 – present

    Project: Borno OCR — funded by the ICT Ministry of Bangladesh

    Leading enterprise deep learning OCR for Bengali text recognition, document layout analysis, and automated PDF/image → editable DOCX.

    • Architected dots.ocr backend integration for Bengali, scaling to 10,000+ documents daily.
    • Optimized Qwen2.5-VL with 4-bit quantization: ~4× memory reduction and ~40% lower infrastructure cost.
    • Proprietary bounding-box alignment: +25% conversion accuracy, −80% manual corrections.

    Project: AI Interview Bot — real-time voice interview platform

    Built the full interview engine and LiveKit WebRTC voice pipeline for automated AI-driven candidate interviews with session-isolated RAG and automated evaluation.

    • End-to-end voice pipeline (STT/LLM/TTS): ~sub-3s average turn latency; 4-tier TTS fallback for ~99% synthesis uptime.
    • Session-isolated RAG: 10+ concurrent interviews with independent CV/JD context; zero cross-session data leakage.
    • Automated evaluation replacing ~20 min manual review per candidate; job-level analytics across multiple roles.
  2. Data Scientist

    Pixalate Inc. Remote · California, USA · Mar 2025 – Aug 2025

    Project: Ad Intel Crawler — AI-powered ad network detection

    AI-driven large-scale web crawling, automated ad network identification, and real-time media analysis for advertising intelligence.

    • End-to-end detection system: 73% accuracy across 2M+ websites, 50K+ pages/day.
    • Deterministic pattern matching: reduced AI dependency, $50K+/year compute savings.
    • Scalable crawler orchestration: 1M+ requests/day with asynchronous processing.
  3. AI Engineer

    Green Pants Studio Remote · Texas, USA · Jun 2024 – May 2025

    Project: Vendidit — AI eCommerce intelligence

    Large-scale scraping, automated fair market valuation, and intelligent data mapping.

    • Vendidit Scraper: +40% speed, 100K+ products/day.
    • OLS regression for valuation: 92% accuracy, −60% pricing errors.
    • Dockerized microservices: −50% deploy time, +35% reliability.
  4. Machine Learning Engineer

    Apurba Technologies Ltd. On-site · Dhaka, Bangladesh · Mar 2023 – May 2024

    Project: Bengali OCR — ICT Ministry funded

    Deep learning OCR for Bengali, layout analysis, and scene text for government digitization.

    • YOLOv8 document layout: 85%+ accuracy on Bengali documents.
    • 8-bit quantization: 2× faster inference, 50% less memory.
    • Co-authored peer-reviewed papers at ACM SE ’24 and Springer (ICTCS / LNNS).
  5. Teaching Assistant, Computer Science & Engineering

    University of Liberal Arts Bangladesh (ULAB) On-site · Dhaka, Bangladesh · Feb 2021 – Jan 2023

    Supported core undergraduate CS courses for cohorts of 30+ students per offering.

    • Courses: Introduction to Programming, Object-Oriented Programming, Artificial Intelligence, Software Engineering.
    • Led lab sessions and tutorials; prepared lab materials; graded assignments and projects.
    • Office hours and one-to-one mentoring, including guidance on AI/ML course projects.

Technical skills

Programming & development

Python (expert), TypeScript, SQL, RESTful APIs, modular service architecture

Machine learning & AI

PyTorch, TensorFlow, scikit-learn, Sentence Transformers, Hugging Face, faster-whisper, Piper (TTS), vLLM, Ollama, LLM integration, deployment, OpenCV, EAST/CRNN handwritten OCR, QAT, DataParallel

Deep learning & NLP

LangChain, RAG, ChromaDB, transformers, GPT/Qwen workflows, semantic search, prompt engineering

Backend & data

FastAPI, WebSockets, LiveKit/WebRTC, SQLite, Redis, SQLAlchemy, PostgreSQL, pgvector, Pydantic, rate limiting, HTTP microservices

Web automation & discovery

Playwright, Crawl4AI, browser-use, BeautifulSoup4, Scrapy, async crawling pipelines

Frontend & DevOps

Gradio, Next.js, React, Docker, Docker Compose, GitHub Actions, CI/CD, Pytest, Vitest

Data science & analytics

Pandas, NumPy, Matplotlib, Seaborn, MLflow, Weights & Biases, statistical analysis

Tools & collaboration

Git, GitHub, Jira, Notion, Slack, Agile, project management

Research & Technical Projects

Production-oriented systems aligned with current work: OCR, matching platforms, full-stack voice agents (REST/WebSocket + optional LiveKit), and RAG.

SenseScan

Bengali handwritten document OCR

Full-page Bengali handwriting: EAST + LANMS detection, CRNN recognition with QAT-ready checkpoints, reading-order assembly. FastAPI endpoints (/plugin, /v1/ocr/handwritten), optional Gradio UI, DataParallel multi-GPU.

Python · PyTorch · FastAPI · OpenCV · LANMS · Gradio

GitHub →

GradConnectAI

Supervisor discovery & matching

End-to-end platform: CV signal extraction, AI-driven professor/opportunity discovery, ranked matches with evidence and outreach drafts.

FastAPI · Next.js · TypeScript · PostgreSQL · pgvector · Playwright · Docker

GitHub →

Voice Healthcare Agent

Full-stack conversational agent (FastAPI · Next.js 14)

Open-source monorepo: FastAPI backend with Next.js /call UI—REST and WebSockets for STT/TTS and agent turns, plus optional LiveKit WebRTC via a dedicated worker calling the same API. Uses Ollama, faster-whisper, and Piper; SQLite for appointment tooling and transcript persistence aligned across transports; optional MuseTalk lip-sync. Backend and frontend CI with pytest and Vitest.

Python · TypeScript · FastAPI · Next.js · LiveKit · Ollama · Docker Compose · GitHub Actions

GitHub →

AI Interview Bot

Real-time voice interview platform

LiveKit WebRTC voice pipeline (faster-whisper STT, Ollama LLM, multi-backend TTS) with session-isolated concurrent interviews. Interview engine handles CV/JD parsing, ChromaDB RAG, ATS scoring, evaluation worker (LLM rubrics + deterministic fallback), and transcript APIs. Rate limiting (Redis/in-memory), turn-level prompt injection defense, Next.js candidate UI with mic/cam pre-checks.

Python · FastAPI · LiveKit · Next.js · ChromaDB · Redis · pytest · Docker

GitHub →

RAG local chat

Document Q&A

Streamlit app with RAG for document-based Q&A—high query accuracy and fast responses in a local setup.

Python · ChromaDB · LangChain · Ollama · Streamlit

GitHub →

Real-time parking tracking

YOLOv9 + tracking

Vehicle detection and tracking at 30 FPS with 92%+ detection accuracy.

PyTorch · OpenCV · Ultralytics · YOLOv9

GitHub →

Publications

Education

University of Liberal Arts Bangladesh (ULAB)

Dhaka, Bangladesh · Jun 2019 – Feb 2023

B.Sc. Computer Science and Engineering

  • Summa Cum Laude — top 1% of graduating class
  • CGPA: 3.96 / 4.00
  • Honors: Vice Chancellor’s Honors List; Dean’s List Scholarship (3×)
  • Coursework: Machine Learning, AI, Data Structures & Algorithms, Software Engineering, Computer Vision, NLP

Honors & awards