Rahul Roy profile photo 1 on Tal

Rahul Roy

Forward Deployed AI Engineer | Building & Deploying AI Systems for Enterprise | LLMs • Agents • RAG • AWS

Mumbai

2+ years of work experience

OnFinance AI
May 20265 mosPresent

Mumbai, Maharashtra, India

- Deployed AI solutions across 5+ enterprise customers, supporting 100+ users and production BFSI workflows. - Designed production-grade RAG pipelines for complex financial regulations, processing 70K+ regulatory documents with versioned embeddings and citation-grounded responses. - Built and shipped AI-powered features generating $100K+ in customer/revenue impact, taking solutions from prototype to production. - Developed end-to-end AI systems spanning LLM pipelines, backend services, databases, cloud infrastructure, and enterprise deployments. - Engineered LangGraph + Bifrost agentic workflows processing 1B+ tokens/month across compliance and financial AI products.
Banyan Intelligence
Jul 202510 mosApr 2026

Bengaluru, Karnataka, India

- Built on-prem AI agents for Indian Telecom Giants, answering queries on Network Parameters like Mobility, Retainability, throughout,etc. - Used and optimised multiple local LLMs for task specific use cases - text2sql generation - Optimised the speed and accuracy of the AI agent in space and compute constraints - Experimented with different LLM inference servers like ollama, llamacpp, vLLM.
Crestron Electronics
Jan 20256 mosJun 2025

Bengaluru, Karnataka, India

- Built an authentication layer for the control system devices. - Ported the old lighttpd(1.4.2) authentication to the new lighttpd(1.4.7)
Banyan Intelligence
Dec 20247 mosJun 2025

Bengaluru, Karnataka, India

Built an MVP for an AI powered interview agent that chats with users over WhatsApp, email or web capturing feedback that feels like human.
System Consultant Information India
Jul 20235 mosNov 2023

Remote

Front-end and Blockchain developer.
BuidlersTribe
Nov 20222 mosDec 2022

Bengaluru, Karnataka, India

Rahul’s AI Stack

claude code
claude code
cursor
cursor
gemini
gemini
hugging face
hugging face
minimax
minimax
opencode
opencode

Education

RV College of Engineering

Bachelor of Technology - BTech, Electrical, Electronics and Communications Engineering

RV College of Engineering

20214 yrs2025
FIITJEE

FIITJEE

Join Rahul and 10k+ other professionals on

Tal Boss

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

Download Tal Boss

Rahul Roy on Tal

Headline

Forward Deployed AI Engineer | Building & Deploying AI Systems for Enterprise | LLMs • Agents • RAG • AWS

About

- Forward Deployed AI Engineer building and deploying production AI systems for BFSI regulators and regulated entities. - Work across LLMs, AI agents, RAG, on-prem AI, LLM inference, and backend systems, taking AI from experimentation to production. - Focused on solving real-world constraints around compute, latency, data, security, and deployment. - Previously at Banyan Intelligence, built on-prem AI agents for telecom enterprises and optimized local LLMs for use cases including Text-to-SQL. - Interested in building reliable, scalable AI systems that solve real business problems.

Location

Mumbai

AI stack

claude code

cursor

gemini

hugging face

minimax

opencode

Work experience

Forward Deployed AI Engineer at OnFinance AI, May 2026 - Present · 5 mos, Mumbai, Maharashtra, India, - Deployed AI solutions across 5+ enterprise customers, supporting 100+ users and production BFSI workflows. - Designed production-grade RAG pipelines for complex financial regulations, processing 70K+ regulatory documents with versioned embeddings and citation-grounded responses. - Built and shipped AI-powered features generating $100K+ in customer/revenue impact, taking solutions from prototype to production. - Developed end-to-end AI systems spanning LLM pipelines, backend services, databases, cloud infrastructure, and enterprise deployments. - Engineered LangGraph + Bifrost agentic workflows processing 1B+ tokens/month across compliance and financial AI products.

Software Engineer at Banyan Intelligence, Jul 2025 - Apr 2026 · 10 mos, Bengaluru, Karnataka, India, - Built on-prem AI agents for Indian Telecom Giants, answering queries on Network Parameters like Mobility, Retainability, throughout,etc. - Used and optimised multiple local LLMs for task specific use cases - text2sql generation - Optimised the speed and accuracy of the AI agent in space and compute constraints - Experimented with different LLM inference servers like ollama, llamacpp, vLLM.

Firmware Intern at Crestron Electronics, Jan 2025 - Jun 2025 · 6 mos, Bengaluru, Karnataka, India, - Built an authentication layer for the control system devices. - Ported the old lighttpd(1.4.2) authentication to the new lighttpd(1.4.7)

SWE Intern at Banyan Intelligence, Dec 2024 - Jun 2025 · 7 mos, Bengaluru, Karnataka, India, Built an MVP for an AI powered interview agent that chats with users over WhatsApp, email or web capturing feedback that feels like human.

Project Engineering Intern at System Consultant Information India, Jul 2023 - Nov 2023 · 5 mos, Remote, Front-end and Blockchain developer.

Operations Intern at BuidlersTribe, Nov 2022 - Dec 2022 · 2 mos, Bengaluru, Karnataka, India

Education

Bachelor of Technology - BTech, Electrical, Electronics and Communications Engineering, RV College of Engineering

FIITJEE