Ashutosh Bansal profile photo 1 on Tal

Ashutosh Bansal

CSE'27 Manipal Institute Of Technology

Bengaluru

1+ year of work experience

INDmoney
May 20263 moAug 2026

Gurugram

Architected an end-to-end NRI bank statement extraction pipeline using MarkItDown and Gemma 4B, handling complete document parsing, structured field extraction, and output generation for a previously unsupported user segment – Improved extraction accuracy by 8–10% on bank statement and ITR pipelines by rebuilding the extraction system; optimized LLM prompts across 5 KYC document types – Leading CVL KYC infrastructure revamp – updating core system architecture to comply with new regulatory requirements, integrating updated CVL APIs and rebuilding affected verification flows end-to-end – Improved OCR pipeline accuracy by 8% via image preprocessing (noise reduction, contrast normalization, skew correction); evaluated HyperVerge and 3+ platforms on accuracy, latency, and reliability to inform platform selection
Office of Corporate Engagement and Career Advisory Services, MITB
Mar 20259 moDec 2025

Bengaluru

MyGov India
Apr 20241 yr 2 mosMay 2025

Ashutosh’s AI Stack

antigravity
antigravity
claude code
claude code
mcp
mcp
ollama
ollama
windsurf
windsurf
Supabase
Supabase

Education

Manipal institute of technology

Bachelor of Technology - BTech, Computer Science

Manipal institute of technology

20234 yrs2027
K. L. International School

K. L. International School

201211 yrs2023

Join Ashutosh and 10k+ other professionals on

Tal Boss

Tal is the app where bosses meet engineers & builders directly, without middlemen

Download Tal Boss

Ashutosh Bansal on Tal

Headline

CSE'27 Manipal Institute Of Technology

Location

Bengaluru

AI stack

antigravity

claude code

mcp

ollama

windsurf

Supabase

Work experience

Software Engineer at INDmoney, May 2026 - Aug 2026 · 3 mo, Gurugram, Architected an end-to-end NRI bank statement extraction pipeline using MarkItDown and Gemma 4B, handling complete document parsing, structured field extraction, and output generation for a previously unsupported user segment – Improved extraction accuracy by 8–10% on bank statement and ITR pipelines by rebuilding the extraction system; optimized LLM prompts across 5 KYC document types – Leading CVL KYC infrastructure revamp – updating core system architecture to comply with new regulatory requirements, integrating updated CVL APIs and rebuilding affected verification flows end-to-end – Improved OCR pipeline accuracy by 8% via image preprocessing (noise reduction, contrast normalization, skew correction); evaluated HyperVerge and 3+ platforms on accuracy, latency, and reliability to inform platform selection

Junior placement committee member at Office of Corporate Engagement and Career Advisory Services, MITB, Mar 2025 - Dec 2025 · 9 mo, Bengaluru

Campus Ambassador at MyGov India, Apr 2024 - May 2025 · 1 yr 2 mos

Education

Bachelor of Technology - BTech, Computer Science, Manipal institute of technology

K. L. International School

Public links

github: https://github.com/ashutoshb206

leetcode: https://leetcode.com/ashu2608

ashutosh.is-a.dev: https://ashutosh.is-a.dev/

Ashutosh Bansal - Software Engineer in Bengaluru | Tal