Headline

Full-Stack+AI Engineer | Building Scalable Products with Cloud Infrastructure & LLM-Powered Systems.

About

I build full-stack applications that leverage large language models (LLM) and retrieval-augmented generation (RAG) to solve real-world problems. With strong backend skills and experience in cloud infrastructure using Docker, Kubernetes, and AWS, I deliver scalable, production-ready software.

Location

Chennai

AI stack

claude code

grok

hermes agent

hugging face

kimi

langchain

Work experience

AI Engineer | LLM Solutions Developer at Freelance, Jul 2025 - Oct 2025 · 4 mos, Remote, - Designed and developed an AI-powered social media assistant for copywriters using LLMs and Chroma embeddings, automating content generation and reducing manual writing time by 40%. - Built an end-to-end inspiration-based text generation pipeline leveraging semantic search, prompt-engineering, and large language models, achieving 95% stylistic consistency with the client’s tone. - Delivered a fully functional AI assistant product tailored to the client’s workflow, enabling the generation of up to 15 high-quality posts per hour.

Full-stack Developer at Team SRM Hackathon, Oct 2024 - May 2025 · 8 mos, Chennai, Tamil Nadu, India, - Contributed to building AI-powered solutions leveraging large language models (LLMs) and retrieval-augmented generation (RAG) during hackathons. - Collaborated with the team to design and implement full-stack features, focusing on scalable and efficient software development.

Education

Bachelor of Technology - BTech, Computer Science, S.R.M Institute of Science and Technology

SRM IST Chennai

Public links

github: https://github.com/Keshav-chand

portfolio-keshavchand.netlify.app: https://portfolio-keshavchand.netlify.app/