Hi, I'm Deep Rathi - AI Engineer at Key
I'm passionate about building machine learning systems that deliver speed and real-world impact. My focus is on cutting-edge generative AI and optimizing real-time inference, turning complex research into fast, reliable production solutions. I thrive where speed is critical.
At a glance
Curated signals on strengths, focus areas, and how they can help.
Interned at Binghamton University on foundational AI research.
Currently an AI Engineer at Key, focusing on generative AI and real-time inference.
Can help others by sharing expertise in low-latency systems and generative AI deployment.
🚀 Career trajectory
Foundational AI Research
Gained initial AI and machine learning experience through research internships in computer vision and data science.
✦ Research
✦ Computer Vision
✦ Data Science
Low-Latency Systems Engineering
Developed specialized skills in high-frequency trading systems, focusing on microsecond-level optimization and performance.
✦ Trading Systems
✦ Low-Latency
✦ Optimization
Generative AI & Real-Time Inference
Currently focused on building and optimizing generative AI models and real-time inference pipelines.
✦ Generative AI
✦ LLMs
✦ Real-Time Inference
💪🏻 Superpowers
Low-Latency System Architect
Engineering for speed in critical applications
✦ Expertise in building low-latency trading systems.
✦ Optimizing real-time inference for generative AI.
✦ Skilled in multithreading and high-performance computing.
Generative AI Innovator
Developing cutting-edge AI models
✦ Currently developing advanced generative AI models.
✦ Leveraging Large Language Models (LLMs) for novel applications.
✦ Proficient with TensorFlow and PyTorch frameworks.
Production-Ready AI Specialist
Bridging research to real-world deployment
✦ Proven ability to deploy AI into production environments.
✦ Experience translating complex AI research into practical systems.
✦ Focus on turning AI concepts into reliable, scalable solutions.
I'm excited about
✦ Connecting with forward-thinking AI researchers and engineers.
✦ Exploring collaborations on cutting-edge generative AI projects.
✦ Discovering opportunities to optimize high-performance computing systems.
I can help with
✦ Share expertise in building low-latency and real-time inference systems.
✦ Provide insights into optimizing machine learning model performance.
✦ Collaborate on developing and deploying generative AI solutions.
I would love your help on
✦ Recommendations for novel applications of LLMs.
✦ Insights into scaling distributed AI systems.
✦ Connections to teams pushing the boundaries of AI hardware acceleration.