Skip to content
View HemanthIITJ's full-sized avatar

Block or report HemanthIITJ

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
HemanthIITJ/README.md

Hemanth Kandimalla

AI Research Engineer · Foundation Models · Agentic Systems

I started with a machine that could not hear.

It received only numbers sampled from an audio signal. Yet somewhere between those samples and a decision about who was speaking, information had to become representation—and representation had to become understanding.

That problem changed the way I looked at computing.

Speech led me to language. Language raised a harder question: why should machine understanding end with words? That curiosity pulled me toward vision and multimodal intelligence, and eventually deeper into the machinery itself.

I stopped being satisfied with seeing a model work.

I wanted to know why it worked, where the information moved, what the objective optimized, what changed during training, and what finally happened on the hardware.

That path took me through model architectures, tokenization, objectives, gradients and distributed training—and then beneath them into precision, kernels, memory movement, parallelism, KV caches, batching and inference.

Because a model can be remarkably intelligent and still become a poor system.

Then another boundary appeared.

A model can reason. A model can call a tool. Neither makes it autonomous.

Autonomy begins when capability is surrounded by control.

That is where much of my current thinking lives: harnesses that turn goals into context and execution; delegate work across models, skills and tools; maintain useful memory; observe their environment; evaluate their own progress; verify outcomes; and decide when to continue, repair, recover—or stop.

The thread across all of this has remained surprisingly constant:

from signals to representations, representations to models, models to systems, and systems to intelligence that can act.

I am less interested in making AI look intelligent.

I want to understand what makes intelligence work, persist, and remain reliable when the real world pushes back.

Pinned Loading

  1. Agent-Skills Agent-Skills Public

    Forked from MicrosoftDocs/Agent-Skills

    Curated Agent Skills for Microsoft & Azure – giving AI coding assistants structured, real-time expertise from Microsoft Learn docs.

  2. AgentFlow AgentFlow Public

    Forked from lupantech/AgentFlow

    AgentFlow: In-the-Flow Agentic System Optimization for Effective Planning and Tool Use

    Python

  3. claude-code claude-code Public

    Forked from anthropics/claude-code

    Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…

    Python

  4. codex codex Public

    Forked from openai/codex

    Lightweight coding agent that runs in your terminal

    Rust

  5. google-research google-research Public

    Forked from google-research/google-research

    Google Research

    Jupyter Notebook

  6. skills_nvidia skills_nvidia Public

    Forked from NVIDIA/skills

    AI agent skills published by NVIDIA

    Python