m
malharj

Malhar J

@malharj

AI Engineer Senior Compiler Engineer

India
Engels, Hindi
Sommige informatie wordt in het Engels weergegeven.
Over mij
I’m an AI and Compiler Engineer focused on building high-impact, business-driven solutions. With 8+ years of experience, I specialize in LLVM-based CPU/GPU compilers, ML/AI compilers, transpilers, and DSLs. I bring strong expertise in computer vision, generative AI, and reinforcement learning, along with full-stack development experience. Through my startup, RealDeed, I’ve also developed deep domain knowledge in real estate across India and the UAE.... Lees meer

Skills

m
malharj
Malhar J
offline • 
Gemiddelde reactietijd: 1 uur

Bekijk mijn diensten

Bugfixes
I will optimize your code for high performance

Werkervaring

Imperial_College London

AI Research Assistant

Imperial College London • Fulltime

Jul 2016 - Sep 20162 mos

Worked as Research Assistant at Imperial College London. Currently Neural networks make incorrect predictions with high confidence (eg: high softmax output). This can be a big problem, especially in the context of safety-critical applications like autonomous vehicles where "trust" on the output is important. This project explored a method to prevent the network from making a prediction whenever it is uncertain (epistemic) about an input. Explored Bayesian methods for Predictive Uncertainty Estimation in Neural Networks in presence of ambiguous inputs. The task was to find a way to make the Neural network say “I know” or “I don’t know” on seeing an ambiguous input. For inputs that are classified as "I don't know", the network can refrain from making a prediction (and hence reduce confident but false predictions). Work involved Literature survey and prototyping a solution (using Tensorflow, Numpy, etc.). The literature survey involved reading up work on Bayesian Networks (MCDropout, GPDNN, BNN, CNN) and papers from important ML conferences like NIPS, ICML, etc.