Vol. 01 — No. 26July 2026

Uday Raj Singh

Generative AI Engineer & Python Developer

GENERATIVE AIRAG PIPELINESLANGCHAINPYTHONFASTAPIVECTOR DATABASESHUGGING FACELLM AGENTSPROMPT ENGINEERINGAWSDOCKERWHISPER

Overview

Generative AI Engineer with hands-on experience building AI-powered systems, document understanding pipelines, and multimodal agents using Python, LangChain, Hugging Face, embeddings, and vector databases. Skilled in designing scalable AI workflows, integrating microservice-based APIs, and deploying production-grade AI solutions — now seeking to push deeper into RAG, conversational intelligence, and cloud-native AI architectures on AWS Bedrock and SageMaker.

Get In TouchView Projects

Skills & Technologies

Skills

Languages

  • Python
  • Java
  • SQL

Frameworks

  • FastAPI
  • Flask
  • LangChain
  • Hugging Face
  • PyTorch
  • OpenCV

GenAI & LLM Stack

  • LLaMA
  • OpenAI GPT
  • Gemini
  • Whisper
  • RAG Pipelines
  • Embeddings
  • Vector DBs
  • Fine-tuning

Cloud & AWS

  • S3
  • DynamoDB
  • EC2
  • Vercel
  • Docker
  • GitHub

Databases

  • PostgreSQL
  • MongoDB
  • Firebase RTDB

Other Tools

  • Postman
  • Cursor
  • Copilot
  • REST APIs

Work Experience

Experience

Software Engineer

Sept 2025 — Present

Mindnerves Technology Services · Pune, India

  • Developing AI-powered engines for a Human Resources application.
  • Designing recommendation workflows with embeddings, vector databases, and LLM pipelines for personalized job matching.
  • Collaborating with cross-functional teams to integrate the engine with existing HR modules and APIs.

Software Developer

Nov 2024 — July 2025

ZFin Tech Pvt Ltd · Lucknow, India

  • Designed backend services with FastAPI and Flask for AI-driven applications with scalable, modular REST APIs.
  • Built LLM-powered features: conversational agents, offline meeting summarizers, and document Q&A with Whisper, OpenAI, and Gemini.
  • Integrated embeddings, vector search, and structured JSON outputs for reliable RAG-style interactions.
  • Implemented prompt-engineered pipelines to improve accuracy, reduce hallucinations, and handle multi-turn queries.
  • Optimized cloud deployments (Vercel, AWS) and API performance for latency and stability.

Software Development Intern

Aug 2024 — Oct 2024

Airtrik · Noida, India

  • Assisted in development and testing of web-based automation solutions using Python.
  • Participated in API integration, bug fixing, and code reviews for client projects.
  • Documented workflows and improved software deployment processes with senior engineers.

Featured Projects

Projects
Project 01

Document AI + Visual Q&A

Offline Meeting Minutes Generator

  • Complete offline document-understanding pipeline using Whisper transcription and LLMs for structured meeting minutes.
  • Interactive Q&A over transcripts using embeddings and RAG-style retrieval workflows.
  • Visual mind maps generated from summarized content for fast comprehension.
  • Zero external model calls — full privacy for enterprise data-sensitive use cases.
WhisperLLMsEmbeddingsRAG
Project 02

sharely.fun

Sharely — Privacy-First File Sharing

  • Secure file-sharing service with server-side encryption and temporary cloud storage retention.
  • FastAPI backend, React (Vite + Tailwind) frontend, storage via Backblaze B2.
  • Scalable API endpoints compatible with AWS S3 architectures.
  • Automatic data expiry workflows mirroring S3 lifecycle policies.
FastAPIReactBackblaze B2Encryption
Visit the Site

Education

Academic Background
00

Master of Computer Applications (MCA)

Specialization: Data Science

Bennett University · Sept 2023 — July 2025

CGPA 0.00 / 10.0

Python, OOP, API Development, Machine Learning, Deep Learning, NLP, DBMS

00

Bachelor of Computer Applications (BCA)

BBD University · Aug 2020 — June 2023

CGPA 0.00 / 10.0

Python & Java, Data Structures, Web Development, Operating Systems, Computer Networks