AI & ML Engineer - NLP, DL, OCR Specialist

Anish Sarkar

B.Tech (AIML), Dept. of CSE, Netaji Subhash Engineering College, Kolkata

Email: ***.********@*****.*** • College: ***********.********@****.**.** • GitHub: ans036 • Phone: +91-987******* EDUCATION

• B.Tech (AI & ML) — Netaji Subhash Engineering College, Kolkata 2021–2025 CPI: 8.77/10

• WBCHSE (XII) 93.2% (2021)

• WBBSE (X) 92.9% (2019)

PUBLICATIONS & MANUSCRIPTS

• Under Review (JCON): “Biologically Consistent Universal Differential Equations for Tumor–Immune Dynamics: Towards a More Interpretable Approach.”

https://proceedings.juliacon.org/papers/a0c88982993ebd268baecc1a2a70305a TECHNICAL SKILLS

Languages: Python, Java, Julia • Skills: Scientific ML, Deep Learning, NLP, OCR, TTS, Data Analytics, DSA, Unit Testing, Accessibility • Libraries/Tools: TensorFlow, PyTorch, Scikit-learn, NumPy, Pandas, Matplotlib, Seaborn, OpenCV, pytesseract, React, Flask

INTERNSHIP EXPERIENCE

• System Product Developer Intern — Bongo Shruti (Assistive Reading System) Feb 2025 – Present Jadavpur University & IIT Kharagpur

Co-developed Bongo Shruti: end-to-end Bengali assistive reading (OCR TTS) with keyboard-only, accessible controls; user studies with 204 visually impaired students.

Refactored Python/OpenCV pipeline, raising character recognition accuracy from 80% to 95% across varied fonts and degraded prints; telemetry-driven UX refinements.

Poster accepted at EMPOWER 2025 (IIT Delhi); see Conference Presentations.

• Software Developer Intern Jul 2024 – Sept 2024

Jadavpur University

Built LLM-based NLP applications improving learning comprehension; launched an AI word-building game engaging 123 users.

Delivered 23% processing efficiency gain via a Transformer + N-gram strategy.

• Machine Learning Intern Feb 2024 – May 2024

Doyen Diagnostics

End-to-end ML pipeline improved disease-burden prediction by 15%.

Semi-supervised DNN (Label Propagation, Gaussian kernel) achieved robust health-score modeling from 78 labeled samples. KEY PROJECTS

• Schizophrenia Classification using EEG [GitHub] Jul 2024 – Oct 2024 Under: Mr. Saikat Biswas (Faculty, CSE, NSEC) — Extracted PSD/DE/SE features; generated 50k scalp heatmaps; Chrononet-inspired CNN achieved 99% accuracy.

• Highway Traffic Flow Classification [GitHub] Aug 2023 – Sep 2023 Two-stream spatio-temporal network improved accuracy by 40% vs. ConvLSTM baseline (84.8% vs. 44.04%); classified 1,000 real-world CCTV instances.

CONFERENCE PRESENTATIONS

• Presented: “Modeling Tumor-Immune Dynamics for Optimized Cancer Treatments,” JuliaCon 2025 (Lightning Talk), Carnegie Mellon University, Pittsburgh, July 23, 2025.

• Presented Poster: “Bongo Shruti: Bengali OCR-to-TTS Assistive Reading System,” EMPOWER 2025, IIT Delhi. ACHIEVEMENTS & INTERESTS

• IBM “Machine Learning Specialist — Associate” badge • Author of poetry book Tales of Grey (verify link)

Contact this candidate