Vicky Choudhary

Associate Software Engineer – Generative AI

Noida, India 1+ yrs exp 73 · Very Good

About

No bio added yet

Skills & Expertise (21)

Python Advanced

8.0/10

Years Exp

LLMs Advanced

8.0/10

Years Exp

Prompt Engineering Advanced

8.0/10

Years Exp

LangChain Advanced

8.0/10

Years Exp

LangGraph Advanced

8.0/10

Years Exp

RAG Advanced

8.0/10

Years Exp

FastAPI Advanced

7.5/10

Years Exp

Microsoft Azure Advanced

7.5/10

Years Exp

Elasticsearch Intermediate

7.0/10

Years Exp

Databricks Intermediate

7.0/10

Years Exp

Docker Intermediate

6.5/10

Years Exp

Git Intermediate

6.0/10

Years Exp

Qdrant Intermediate

6.0/10

Years Exp

Postgres Intermediate

5.5/10

Years Exp

MySql Intermediate

5.5/10

Years Exp

Redis Intermediate

5.0/10

Years Exp

CSS Intermediate

5.0/10

Years Exp

HTML Intermediate

5.0/10

Years Exp

C++ Beginner

4.0/10

Years Exp

Langsmith MLflow

Work Experience

Associate Software Engineer – Generative AI

Altysys

Jun 2025 - Present

Developed a document update system that applies amendment instructions to base documents. Converted base documents into structured HTML using parsing libraries, while amendments were modeled in JSON. Integrated LLMs to process both sources and generate updated, legally accurate PDFs. Designed and implemented a microservices-based architecture using FastAPI, enabling modular and independently deployable services. Ensured both base and amendment documents were fetched from a unified knowledge base. Deployed the document processing and LLM-powered workflow on Microsoft Azure, enabling scalable and reliable cloud-based execution. Automated the full workflow, improving efficiency in handling versioned legal/technical documents.

GenAI Intern

Altysys

Jul 2024 - Jan 2025

Built an RAG-based chatbot supporting Excel, CSV, PDF, DOCX, PPTX, and image files. Used Azure Document Intelligence to extract content while retaining table integrity. Improved document upload speed by 62.5% using multithreading and load balancing. Implemented Elasticsearch + ‘text-embedding-3-small‘ for efficient vector retrieval. Integrated pipelines on Databricks for scalable vector storage and query optimization. Refined prompts for accurate, context-aware responses and deployed models via Databricks MLflow.