SARVESH GANESAN

AI Research Engineer

Building the future with AI, one algorithm at a time

AI/ML

Engineering

Data

Engineering

Cloud

Infrastructure

About Me

AI Engineer with more than 2 years of experience in designing and implementing generative AI solutions, specializing in autonomous AI agents.

Proficient in Python, AWS, and vector databases, with a strong command of LangChain, RAG systems, and prompt engineering techniques. Demonstrated ability to create scalable ML/AI solutions from the ground up, while collaborating effectively with cross-functional teams to deliver high-quality software products.

Career aspirations include further enhancing technical expertise and contributing to innovative AI initiatives. Currently researching novel approaches to improve RAG retrieval accuracy by experimenting with SLM and LLMs combined with vector databases.

Generative AI

Building conversational AI and autonomous agent solutions using LLMs, RAG systems, and advanced prompt engineering

Cloud Infrastructure

Scalable AWS architectures with Bedrock, EKS, Lambda, and CI/CD pipelines for secure operations

Data Engineering

Distributed ETL with Apache Spark, Iceberg, and vector databases for intelligent data operations

Experience

09/2023 - Current

AI Research Engineer

Groundzero Software Private Limited · Chennai

  • Developed and deployed conversational AI and autonomous agent solutions (LLMs, RAG, FastAPI, AWS Bedrock)
  • Architected and implemented an interactive backend, enabling users to run distributed ETL/data transforms directly in-browser, using custom Runtime Environments (Spark, Pandas, DuckDB), provisioned on-demand in containers
  • Built scalable cloud infrastructure for automation, CI/CD, and secure operations using AWS (ECR, EKS, EC2, Lambda, CodePipeline)
  • Created an extensible API catalog, streamlining API development and integration across all platform services
  • Implemented AI Agents to automate datasets, charts, visualization and dashboard generation
  • Integrated ML Libraries in all the custom runtime environments, facilitating inference operations
  • Currently researching a novel approach to improve RAG retrieval accuracy by experimenting with SLM and LLMs combined with vector databases
06/2023 - 08/2023

Software Trainee

SCI-BI Software Solutions Private Limited · Chennai

  • Developed and maintained data visualizations and dashboards using Power BI and Tableau
  • Participated in client meetings to gather requirements and translate them into technical specifications
  • Created reports and presentations, enhancing clients' data-driven decision-making

Technical Arsenal

AI & ML

Generative AI LangChain RAG Systems Prompt Engineering LLMs MLFlow

Cloud Infrastructure

AWS Bedrock EC2 ECR EKS S3 Lambda Docker

Data Engineering

Apache Spark Apache Iceberg PGVector Pinecone FAISS DuckDB

Development

Python FastAPI REST APIs gRPC CI/CD CodePipeline

Featured Projects

AgentSynapse

Enterprise AI agent platform enabling intelligent data analytics automation through specialized agents (SQL, BI, ETL, Analytics) with contextual memory system and comprehensive tool integration for unified data operations.

AI Agents LLMs Data Analytics RAG
View on GitHub

CloudeasyML

Multi-modal ML system for real-time housing market crisis prediction and policy recommendation using XGBoost, CatBoost, TimesFM, and STGNN. Deployed on Kubernetes with GPU support for scalable, enterprise-grade forecasting.

ML Models Kubernetes FastAPI Docker
View on GitHub

AMSR_RAG

Novel approach to improve RAG retrieval accuracy by combining Small Language Models (SLM) and Large Language Models with vector databases for enhanced information retrieval and context understanding.

RAG LLMs Vector DB Research
View on GitHub

Tech Stack

Python
AWS
Docker
PostgreSQL
LangChain
RAG
Spark
Kubernetes
FastAPI
Git

GitHub Activity

--

Repositories

--

Total Stars

--

Recent Commits

--

Day Streak

Recent Activity

Loading activity...

Top Repositories

Loading repositories...

Let's Connect

Ready to build the next generation of AI solutions together?