Hi, I'm Akash Deep.

( )

As an Software Developer, I have a keen ability to swiftly learn new concepts and excel in strategic planning. My consistently positive approach and strong problem-solving skills are complemented by excellent leadership, communication, and interpersonal abilities. I am proficient in Java, Python, Machine learning, and Web Development.

Download CV

About memy stats

About me

Competitive, problem solver, optimistic, creative, and always eager to learn new things with great enthusiasm. I am willing to work in a dynamic and challenging environment, utilizing my skills and knowledge to the best of my abilities. My goal is to contribute positively to my personal growth as well as the growth of the organization.

Download CV

10+

Projects
Completed

0-1

Years of
Experience

My Skills

Python

90%

Java

85%

Machine Learning

85%

LangGraph/LangChain

85%

MCP

80%

Spring Boot

85%

Django/Flask

85%

Pytorch/Tensorflow/OpenCV

85%

LLM

80%

Github

85%

SQL

80%

MongoDB

80%

My Timeline

October 2025-Present

National Payments Corporation Of India (NPCI) | Associate AI Engineer | HYDERABAD

• Engineered a multi-agent LLM system using LangGraph and LangChain to power three core UPI platforms: a contextual Q&A assistant for payment queries, an automated mandate management tracker, and a grievance redressal system for transaction disputes and complaint registration, achieving 92% accuracy in secure workflows.
• Architected hybrid RAG system using Neo4j + Pinecone for UPIHelp Phase 2 that traces payment relationships (user→mandate→merchant→transaction), delivering 35% more accurate answers to complex multi-entity queries compared to vector-only search.
• Orchestrated backend services and agent orchestration layer using MCP (Model Context Protocol) to seamlessly integrate mandate management, grievance redressal, and Q&A capabilities into a unified conversational interface.

October 2024-October 2025

National Payments Corporation Of India (NPCI) | Graduate Engineer Trainee | HYDERABAD

• Designed Pydantic-AI tool-calling infrastructure connecting 15+ UPI APIs for transaction lookup, complaint filing, and mandate status checks, processing 10K+ automated API calls monthly with 45% faster response times.
• Created an enterprise-grade ChatGPT for NPCI employees, ensuring 100% compliance with internal data security policies.
• Built fraud detection ML models for International I-UPI detecting suspicious cross-border payment patterns in real-time, catching 95% of fraudulent transactions while reducing false alarms from 25% to 5% (20% decrease in false positives).
• Developed Whisper-based AI transcription and summarization system for internal meetings and documentation, accelerating report generation by 70% and reducing manual note-taking effort by 50% across teams.
• Orchestrated backend services and agent orchestration layer using MCP (Model Context Protocol) to seamlessly integrate mandate management, grievance redressal, and Q&A capabilities into a unified conversational interface.

September 2024-October 2024

Mioneer Private Limited| Django Intern | Remote

• Created a dynamic garment customization feature using Django, enhancing user experiences and boosting engagement by 30%.
• Optimized database management and query handling, resulting in 20% faster response times and improved application performance.
• Worked closely with cross-functional teams, contributing to feature enhancements and ensuring seamless integration of new functionalities.

July 2024-August 2024

FUTRAINC-COMPLETE BUSINESS SOLUTIONS | AI Developer Intern | REMOTE

• Developed data preprocessing pipeline applying deduplication, validation, and standardization for LLM training datasets, improving data quality by 25%.
• Executed fine-tuning experiments and evaluation runs, optimizing hyperparameters and training data that boosted LLM accuracy by 15% on tasks.
• Documenting experiments and collaborating with team members on innovative AI solutions.

July 2023-August 2023

Celebal Technologies| Data Engineer Intern | Remote

• Crafted a calculator interface with Python’s Tkinter,elevating user engagement by 20% and ensuring good accuracy in arithmetic operations.
• Engineered a bill management system using JavaScript,increasing user sign-ups by 30% and enhancing satisfacti on with secure login and account management.
• Integrated a MySQL database for secure storage of user credentials, achieving Gold Badge recognition for outstanding internship performance.

2020 - 2024

B.Tech CSE - Lovely Professional University

Bachelor of Technology in Computer Science and Engineering
Lovely Professional University, Punjab, India
CGPA: 7.65

2019 - 2020

Class 12th - St.Joseph's School

St. Joseph's School, Bhagalpur, Bihar
Percentage: 81%

2017 - 2018

Class 10th - St.Joseph's School

St. Joseph's School, Bhagalpur, Bihar
Percentage: 81.6%

My ProjectsMy Work

Here is Some Of My Projects that I've done using various Programming Languages.

Electricity Bill Management Image

ELECTRICITY BILL MANAGEMENT SYSTEM

The project aims at serving the department of electricity by computerizing the billing system. It mainly focuses on the calculation of Units consumed during the specified time and the money to be paid to electricity offices.

DYNAMIC TO DO LIST APPLICATION

Architected a dynamic to-do list application using the MERN Stack,enabling real-time task managementand increasing user productivity by 35%.

AD CREATIVE/NON-CREATIVE RECOGNITION

AD CREATIVE/NON-CREATIVE RECOGNITION

Developed a state-of-the-art CNN model achieving 90% validation accuracy in accurately categorizing images into ad creatives and non-ad creatives.

HAND GESTURE RECOGNITION

FOOD RECOMMENDATION SYSTEM USING LLM

Employed OpenCV to access and process web caminput,enabling real-time application of the hand gesture recognition system.

INSTAGRAM CLONE USING DJANGO

INSTAGRAM CLONE USING DJANGO

Developed an Instagram clone using Django, allowing users to post images, like posts, and comment on posts.

QUIZ APP

QUIZ APP

Developed a quiz app with an intuitive user interface that allows users to take quizzes and stores their high scores.

SPRING BOOT CHAT APPLICATION

SPRING BOOT CHAT APPLICATION

Developed the chat application backend using Spring Boot, achieving a 30% reduction in development time, enhanced real-time communication with WebSocket reducing message latency.

ChatBot

CUSTOMER SUPPORT CHATBOT

Designed an interactive chatbot interface using JavaScript and Flask, providing seamless customer support.

Calendar

CALENDAR

Developed an intuitive calendar application with an enhanced user interface and drag-to-select timeline, increasing user efficiency.

Contact MeContact

Contact me here

Lovely Professional University, Phagwara, Punjab, India, 144402

Location

: Bhagalpur,Bihar, India

Email

: 2001akashdeep@gmail.com

Education

: Lovely Professional University(CSE)

Mobile Number

: 9065508862

Languages

: English , Hindi