Hi, I'm Deep Rathi - AI Engineer at Key
I engineer AI for speed and impact, specializing in low-latency, real-time generative AI. My passion is transforming complex research into production-grade applications that perform exceptionally fast in demanding environments. I thrive on pushing the boundaries of what's possible in ML.
At a glance
Curated signals on strengths, focus areas, and how they can help.
Led foundational AI research and engineering at VIT, contributing to early computer vision models.
Currently building high-performance generative AI tools with a focus on real-time inference at Key.
They can provide expertise on optimizing AI models for speed and integrating generative AI into production.
🚀 Career trajectory
Foundational ML & Research
Gained initial experience in machine learning and AI research, including work on autonomous driving models.
✦ Machine Learning
✦ Research
✦ Computer Vision
Low-Latency Systems Specialization
Developed expertise in high-frequency trading systems, focusing on microsecond-level optimizations.
✦ Low-Latency Systems
✦ Trading Systems
✦ Performance Optimization
Generative AI & Real-Time Inference
Currently focused on building and optimizing generative AI models for real-time inference.
✦ Generative AI
✦ Real-Time Inference
✦ Model Optimization
💪🏻 Superpowers
Master of Low-Latency AI
Expertise in optimizing AI for speed-critical applications.
✦ Builds machine learning systems engineered for peak performance.
✦ Specializes in real-time inference and microsecond-sensitive trading systems.
✦ Drives efficiency in generative AI model deployment.
Generative AI Innovator
Pioneering advanced applications of generative AI and LLMs.
✦ Develops cutting-edge generative AI models.
✦ Leverages Large Language Models for novel solutions.
✦ Applies AI research across diverse domains.
Production-Grade AI Engineer
Translating complex AI into robust, real-world solutions.
✦ Focuses on deploying AI into production environments.
✦ Experienced in building and optimizing scalable ML systems.
✦ Expertise in MLOps and real-time system integration.
I'm excited about
✦ Connect with pioneers in real-time AI and distributed systems.
✦ Explore collaborative opportunities in cutting-edge AI research.
✦ Discover emerging trends in high-performance computing and AI infrastructure.
I can help with
✦ Offer expertise in optimizing AI models for speed and efficiency.
✦ Share insights on building low-latency and real-time ML systems.
✦ Provide guidance on integrating generative AI into production environments.
I would love your help on
✦ Identify research groups pushing the boundaries of AI inference optimization.
✦ Find collaborators for novel generative AI applications.
✦ Connect with experts in distributed systems for large-scale AI deployment.
