Hi, I’m Hari

I’m endlessly curious about how things work - from neural networks to neurons, from kernels to complex systems.

What I Do

I build AI systems that bridge research and reality. My technical journey spans neural networks, probabilistic models, reinforcement learning, computer vision, and LLMs. Lately, I’ve been diving deep into GPU programming and systems-level optimization - there’s something beautiful about making code run 100x faster.

I’ve published research at ICAPS and IJCAI, invented new architectures like RSPMNs, and shipped AI products at startups. But what really drives me is the learning itself - that moment when a complex concept suddenly clicks.

What Fascinates Me

My curiosity extends far beyond code. I’m drawn to:

  • The Nature of Reality - From the Big Bang to quantum mechanics, from general relativity to the emergence of biological complexity. How did we get here?
  • Mathematics & Computation - Gödel’s incompleteness theorems, Turing machines, lambda calculus, Bayesian networks, and scaling laws. The foundations that make intelligence possible.
  • Consciousness & Philosophy - How do neurons create experience? What did ancient philosophers mean by Brahman? I explore everything from Advaita Vedanta to the hard problem of consciousness.
  • Complex Systems - Economics, politics, neuroscience - anywhere patterns emerge from chaos. How do markets self-organize? Why do civilizations rise and fall? What makes emergent behavior so beautiful?
  • Movement & Expression - I dance to think with my body, to express what words cannot. I practice Vipassana meditation (survived a 10-day silent retreat that rewired my perspective on reality).

My approach blends contradictions: I meditate yet remain optimistically anxious about humanity’s future. I build rigorous mathematical models while believing consciousness transcends computation. I obsess over technical details but know that in the end, human taste and intuition are what truly matter.

Current Obsessions

  • Building MiniTorch from scratch to understand deep learning at the metal
  • Optimizing CUDA kernels (there’s zen in the optimization)
  • Fine-tuning LLMs for autonomous agents
  • Understanding how consciousness emerges from computation

Let’s Connect

I love conversations that challenge assumptions and open new perspectives. Whether it’s about transformer architectures, economic systems, or the nature of consciousness - if you’re curious about it, I probably am too.

Email | LinkedIn | GitHub

“The only way to do great work is to love what you do, and the only way to love what you do is to never stop learning.”