Hi, I'm Deep Rathi - AI Engineer specializing in low-latency ML and real-time inference
I am obsessed with the challenge of making AI actionable in mere milliseconds. I thrive in high-stakes environments where I bridge the gap between complex model architecture and seamless, high-speed deployment.
At a glance
Curated signals on strengths, focus areas, and how they can help.
Conducted machine learning research at Binghamton University, laying a strong foundation for advanced AI experimentation.
Currently architecting high-performance, low-latency generative AI systems at Key to enable real-time inference.
Provides expert guidance on optimizing ML pipelines and deploying efficient, high-speed generative AI solutions for production.
🚀 Career trajectory
Foundation in Data Science
Began with data analytics and dashboard development, gaining foundational skills in data handling and business insights.
✦ Data Analytics
✦ Data Visualization
✦ SQL
Deep Dive into ML Research
Transitioned to AI research, contributing to autonomous driving models and gaining experience in model training and evaluation.
✦ Machine Learning
✦ Autonomous Driving
✦ Research
Focus on Real-Time AI
Specialized in building low-latency ML systems, focusing on generative AI and optimizing real-time inference for production environments.
✦ Low-Latency Systems
✦ Generative AI
✦ Real-Time Inference
💪🏻 Superpowers
Real-Time ML System Architect
Expert in designing and optimizing machine learning systems for speed.
✦ Develops generative AI models for real-time inference.
✦ Optimizes system pipelines for low-latency ML deployment.
✦ Builds high-performance trading systems where milliseconds matter.
Generative AI Innovator
Pioneering the application of generative AI and LLMs.
✦ Creating advanced generative AI models.
✦ Leveraging Large Language Models for complex tasks.
✦ Automating ML pipelines for enhanced efficiency.
Autonomous Systems Contributor
Experienced in AI for autonomous applications.
✦ Contributed to deep learning models for autonomous driving.
✦ Involved in data annotation and model training.
✦ Applied AI research across various domains.
I'm excited about
✦ Discovering niche AI research communities to collaborate on inference breakthroughs.
✦ Connecting with leading AI architects for future generative model design.
✦ Finding co-founders for a startup focused on edge AI deployment.
I can help with
✦ Offer expertise in optimizing ML models for low-latency environments.
✦ Provide insights into building efficient real-time AI systems.
✦ Share knowledge on developing and deploying generative AI solutions.
I would love your help on
✦ Advanced research opportunities in real-time AI.
✦ Connections to industry leaders in low-latency ML.
✦ Guidance on scaling Generative AI inference.
