Karthik Sathish

AI Researcher

Roorkee, Uttarakhand, India2 yrs experience

AI EnabledAI ML Practitioner

Key Highlights

Experienced in AI and intelligent agents development.
Contributed to blockchain technology through GSoC.
Developed advanced AI models for data retrieval.

Stackforce AI infers this person is a skilled AI developer with experience in blockchain and data retrieval technologies.

Contact

Skills

Core Skills

Artificial Intelligence (ai)Large Language Models (llm)

Other Skills

Intelligent AgentsSoftware AgentsLangChainPython (Programming Language)FlaskRetrieval-Augmented Generation (RAG)Machine LearningBack-End Web Development

About

I love building!

Experience

2 yrs

Total Experience

1 yr 6 mos

Average Tenure

Current Experience

School hack.ai

AI Intern

Aug 2025 – Sep 2025 · 1 mo · Remote

Artificial Intelligence (AI)Intelligent AgentsSoftware Agents

Google summer of code

Contributor

Jun 2025 – Aug 2025 · 2 mos · Remote

I will be contributing to a blockchain based platform under the organisation Alaska

Ceramd ai

AI Intern

Mar 2025 – May 2025 · 2 mos · Remote

Stealth startup

AI (RAG) model developer

Nov 2024 – Jan 2025 · 2 mos · Remote

As an AI Intern at Squarest, I performed the following task:
Firstly, I scraped the data by writing my own scrapping code (thanks to beautiful soap). Already existing scrapping tools such as Firecrawl didn’t give desired content.
Once I got the data, I converted it into chunks using recursive text split, specifying suitable chunk size and chunk overlap parameters.
Converted those chunks into vector embeddings using text-embedding-3-large. Stored in the vector database (Astra Datastax).
Then comes the data retrieval part based on the user query. I made use of MMR (maximum marginal search) and BM25 (best matching 25 ) to fetch the most relevant documents.
Made use of Llama - 2- 8b to display a human readable response by passing both the retrieved documents as well as the user query. The response generated by the user was finally shown on Streamlit (an easy to build web interface ).
The end result : the agent was able to respond to the user query by providing most relevant information surfing the vector database. If the question is irrelevant (out of the domain), then the System Prompt passed to the agent will make sure to reply accordingly to the end user.

Large Language Models (LLM)LangChainPython (Programming Language)