Vedant Joshi

Software Engineer

Pune, India 2+ yrs exp 86 · Excellent

About

Software Engineer with almost 3 years of experience building web applications, AI-powered solutions, and enterprise software. Full-stack across Angular.js, TypeScript, C#, ASP.NET Core, and Python / FastAPI, with hands-on experience in Azure AI services, GenAI agents, RAG, and document intelligence. Record of improving application performance, building developer productivity tools.

Skills & Expertise (47)

LangGraph Advanced

8.0/10

Years Exp

NLP Advanced

8.0/10

Years Exp

Vector Embeddings Advanced

8.0/10

Years Exp

Vector Search Advanced

8.0/10

Years Exp

Prompt Engineering Advanced

8.0/10

Years Exp

Retrieval-Augmented Generation Advanced

8.0/10

Years Exp

Semantic Retrieval Advanced

8.0/10

Years Exp

LLMs Advanced

8.0/10

Years Exp

AI Agents Advanced

8.0/10

Years Exp

Python Intermediate

7.5/10

Years Exp

Caching Intermediate

7.0/10

Years Exp

Azure Intermediate

7.0/10

Years Exp

AWS Intermediate

7.0/10

Years Exp

Docker Intermediate

7.0/10

Years Exp

Kubernetes Intermediate

7.0/10

Years Exp

GitHub Actions Intermediate

7.0/10

Years Exp

Elasticsearch Intermediate

7.0/10

Years Exp

Redis Intermediate

7.0/10

Years Exp

Git Intermediate

7.0/10

Years Exp

Celery Intermediate

7.0/10

Years Exp

Asynchronous Processing Intermediate

7.0/10

Years Exp

Microservices Intermediate

7.0/10

Years Exp

REST APIs Intermediate

7.0/10

Years Exp

Node.js Intermediate

7.0/10

Years Exp

FastAPI Intermediate

7.0/10

Years Exp

MERN Stack Intermediate

7.0/10

Years Exp

React.js Intermediate

7.0/10

Years Exp

Angular.js Intermediate

7.0/10

Years Exp

GitHub Copilot Intermediate

7.0/10

Years Exp

MCP Intermediate

7.0/10

Years Exp

Document Intelligence Intermediate

7.0/10

Years Exp

Typescript Intermediate

7.0/10

Years Exp

JavaScript Intermediate

7.0/10

Years Exp

OCR Intermediate

7.0/10

Years Exp

Semantic Search Intermediate

7.0/10

Years Exp

Agentic Workflows Intermediate

7.0/10

Years Exp

ASP.NET Core Intermediate

6.0/10

Years Exp

C# Intermediate

6.0/10

Years Exp

SQL Intermediate

6.0/10

Years Exp

HTML5 Intermediate

6.0/10

Years Exp

CSS Intermediate

6.0/10

Years Exp

MySql Intermediate

6.0/10

Years Exp

MongoDb Intermediate

6.0/10

Years Exp

Postgresql Intermediate

6.0/10

Years Exp

NUnit Intermediate

6.0/10

Years Exp

.NET Intermediate

6.0/10

Years Exp

C++ Intermediate

5.0/10

Years Exp

Work Experience

Associate Software Engineer

NICE Systems

Jul 2024 - Oct 2026

Developed and shipped features for NICE EvidenCentral, an enterprise digital-evidence-management platform used by 100+ law-enforcement, court, and justice agencies across the UK and US, building responsive interfaces with Angular.js, TypeScript, and C#/.NET across web and mobile portals for investigators, and integrating secure REST APIs for real-time evidence access. Built and product ionized Impact Analyzer, an autonomous AI agent (Python, FastAPI, LangGraph, MCP) that earned internal recognition and was adopted across engineering teams, traversing dependency graphs across 2.5M+ LOC and 120+ services to flag the blast-radius of code changes pre-merge and reduce regression escapes by 40%. Reduced the agent’s P95 analysis latency 74% (42s to 11s) via distributed task queues, parallel LLM graph traversal, and Redis semantic caching, cutting LLM token consumption 65% while sustaining 15+ QPS across 50+ concurrent webhooks. Delivered a proof-of-concept for multi-angle video evidence, synchronizing 4 concurrent camera feeds in a multi-pane player for court-ready review, since adopted into the product roadmap. Optimized the evidence-upload pipeline, raising upload throughput 3x and the per-batch limit from 50 to 500 files, and resolved critical UI slowness, reducing page-load and interaction latency by 50%.

Associate Software Engineer-Intern

NICE Systems

Jan 2024 - Jul 2024

Designed and built a patent-project, full-stack GenAI evidence-intelligence platform (MERN, Python, FastAPI) applying Azure AI Document Intelligence, Computer Vision, and OCR to auto-extract and classify data from 10K+ multi-modal files (scans, images, PDFs, audio) into structured, searchable case records for downstream investigations. Engineered asynchronous processing pipelines with Celery and Redis, parallelizing OCR and ML inference to cut P95 latency by 62% while sustaining 8,000+ pages/min across distributed workers with automatic retries and fault tolerance. Built a hybrid semantic-search layer using Elasticsearch with dense vector embeddings and RAG (P99 retrieval across a 4GB+ corpus); trained Azure ML models (Random Forest) reaching 92% classification accuracy.