SYSTEM BOOTSTRAP


0%

* cards are draggable *
Saunak Ghosh profile photo
Saunak Ghosh mark
FIG_001

Saunak Ghosh

Software Engineer @ Takkada
Open to Work

Overview

Software Engineer @ Takkada
Focus: AI Systems & SaaS
--:--_ // IST
he / him

Social Links

GitHub Contributions990 contributions in the last year
Contribution GraphJulAugSepOctNovDecJanFebMarAprMayJun
Public GitHub activity for Saunakghosh10
Less0 contributions1 contributions2 contributions3 contributions4 contributionsMore
About Me

About

I engineer high-performance AI systems and design scalable backends that power resilient, production-grade full-stack architectures. My work focuses on building autonomous agents and choreographing complex multi-agent orchestration workflows to solve hard, distributed systems problems.
01.
Software Engineer focused on AI, backend systems, and full-stack product development across enterprise and SaaS environments.
02.
Hands-on with Python, TypeScript, Next.js, Supabase, Convex, Docker, Azure, OpenAI API, and Retrieval-Augmented Generation (RAG).
03.
Built systems ranging from LLM fine-tuning pipelines and semantic search to collaborative SaaS products and scheduling platforms.
04.
Currently at Takkada, building AI systems and backend infrastructure with Python, FastAPI, and AWS for enterprise applications.- Implementing ML pipelines and scalable APIs for production workloads.
05.
Previously built a 0-to-1 B2B SaaS lead generation platform at Adaapt.ai with OpenAI, Twilio, semantic search, and concurrent backend systems.- Achieved 85% match accuracy and reduced manual operations by 90%.

Peak metrics recorded; actual figures may vary.

"Built production AI and backend systems with measurable impact across both enterprise and startup environments."

Engineering Focus

"Led frontend delivery for VIT Advitya Fest, supporting 3,000+ active users without crashes during peak load."

Leadership & Execution

Tech Stack

Selected Projects

(14)

I love designing and building thoughtful, production-grade applications.

View Project

Infinity UI preview

Infinity UI

A copy-paste React component library with 37+ beautifully animated components for modern product interfaces.

Live
Open Emergent preview

Open Emergent

A self-hostable AI application builder powered by a 9-agent LangGraph mesh architecture for complex agentic workflows.

Building

View Project

Sarvam Voice preview

Sarvam Voice

A sovereign Voice AI Support Platform designed for Indian enterprise scale, combining speech transcription, agentic reasoning, and voice generation.

ChromaDB
OpenTelemetry
Live

View Project

DesignDeck preview

DesignDeck

A community-driven platform for system design interview prep with level-based curation, AI-assisted submissions, and community voting.

Convex
Clerk
Google Gemini AI
Live
Firecrawl preview

Firecrawl

A high-performance web scraping and crawling engine that feeds clean Markdown or structured JSON directly into LLMs and AI agents.

Playwright
OpenAI API
Building

View Project

StoxMultiplier preview

StoxMultiplier

An AI-powered portfolio analysis platform for Indian investors with broker imports, visual dashboards, and Gemini-powered chat insights.

XLSX
Live

View Project

PathForge preview

PathForge

An interactive learning platform that generates personalized developer roadmaps, hands-on coding challenges, mentorship pathways, and progress tracking.

Convex
Clerk
Live

Experience

(3)

Takkada

Location
Remote
Status
  • Building AI systems and backend infrastructure for enterprise applications.
  • Implementing ML pipelines and scalable APIs for production workloads.
PythonFastAPIPostgreSQLDockerAWS

HCLTech

Location
Remote
  • Architected a generative AI fine-tuning pipeline for TinyLlama and related LLM workflows using Python and Azure Machine Learning.
  • Increased model inference efficiency by 35% while achieving 85% accuracy on domain-specific datasets.
  • Built CI/CD deployment pipelines with Azure DevOps, Docker, and Python, cutting packaging and deployment time by 40%.
PythonAzure MLDockerAzure DevOps

Adaapt.ai

Location
Remote
  • Engineered a 0-to-1 B2B SaaS lead generation platform using Next.js, TypeScript, Supabase, OpenAI API, and Twilio.
  • Implemented RAG and semantic search with vector embeddings to reach 85% match accuracy and reduce manual operations by 90%.
  • Optimized REST APIs and database query thread-safety for concurrent request handling with zero downtime during peak traffic.
Next.jsSupabaseOpenAI APITwilio

Education

  • Maintained a strong academic record with an 8.55 / 10.0 GPA.
  • Specialized in Data Structures, Algorithms, Distributed Systems, Systems Design, and Web Technology.
  • Served as the Web Development Lead for Advitya Fest, building a registration portal that supported 3,000+ active users without downtime.
  • Data Structures
  • Algorithms
  • Systems Design
  • React.js
  • Java
  • Python
  • SQL
  • C++
  • Java
  • Physics
  • Mathematics

Achievements & Leadership

(2)
Academic Excellence - Maintained an 8.55/10.0 GPA in Computer Science at VIT, with strong grounding in Data Structures, Algorithms, and Distributed Systems.
Web Development Lead (Advitya Fest) - Directed frontend engineering for a React.js registration portal that supported 3,000+ active users without failures during peak load.