I'm an AI Engineer focused on building scalable, intelligent backend systems for AI-driven applications. I specialize in conversational AI, retrieval-augmented generation (RAG), and multi-agent orchestration using large language models. My work often bridges the gap between raw unstructured data and production-ready, secure, and efficient backend APIs—leveraging tools like FastAPI, Docker, Redis, and vector databases like Pinecone and AWS AI Search.
I graduated from IIT Bombay. Currently, I’m developing a multi-agent chatbot platform that enables configurable LLM workflows. I love blending deep tech with user-centered design to deliver impactful solutions.
I run a blog where I write about what happens under the hood of large language models—how GPUs execute your code, how inference and training are optimized, and what really powers AI systems at scale.
📬 Check it out here → sameerkankute.substack.com
If you're a developer trying to make sense of LLM internals, scaling bottlenecks, or GPU architecture in practice, there's something in there for you.
- 🌱 Currently exploring LLM agents and streaming architectures
- 💬 Open to discussions on scalable AI systems
- 📫 Reach me at: sameerkankute@gmail.com
- ⚡ Fun fact: Coding and coffee hits harder!
