Hi, I'm Deep Rathi - AI Engineer at Key
I engineer machine learning systems that excel in speed and efficiency, particularly in real-time inference and generative AI. I thrive on transforming complex AI research into robust, production-grade solutions that deliver measurable impact.
At a glance
Curated signals on strengths, focus areas, and how they can help.
Developed low-latency trading systems, honing skills in high-speed computations.
Currently building and optimizing real-time inference and generative AI models.
Can help others by architecting and implementing low-latency ML pipelines.
🚀 Career trajectory
Foundational AI Research
Gained early exposure to AI research and autonomous driving models.
✦ Research Intern
✦ AI Research
Low-Latency Systems Expertise
Developed low-latency trading systems, honing skills in high-speed computations.
✦ Machine Learning Intern
✦ Low-Latency Systems
Real-Time Generative AI Engineering
Currently building and optimizing real-time inference and generative AI models.
✦ AI Engineer
✦ Generative AI
✦ Real-Time Inference
💪🏻 Superpowers
Masters of Real-Time AI
Specializing in low-latency and high-throughput ML systems.
✦ Develops generative AI models for real-time inference.
✦ Optimizes systems where microsecond-level performance is critical.
✦ Leverages C++, WebSocket, and multithreading for speed.
Bridging AI Research to Production
Proven ability to deploy AI models in real-world scenarios.
✦ Transforms AI research into deployable, production-grade systems.
✦ Experience in domains like trading and autonomous driving.
✦ Focuses on practical AI applications with tangible impact.
Generative AI Innovator
Pioneering advancements in LLMs and creative AI.
✦ Currently developing cutting-edge generative AI models.
✦ Utilizes frameworks like TensorFlow and PyTorch for deep learning.
✦ Explores LangChain and other tools for advanced AI applications.
I'm excited about
✦ Exploring novel applications of generative AI in production environments.
✦ Connecting with peers passionate about high-performance AI systems.
✦ Discovering opportunities to collaborate on ambitious AI projects.
I can help with
✦ Architecting and implementing low-latency machine learning pipelines.
✦ Optimizing AI models for real-time inference and performance.
✦ Consulting on generative AI strategies and implementation.
I would love your help on
✦ Insights into emerging trends in real-time AI applications.
✦ Connections with leaders in the generative AI space.
✦ Feedback on novel approaches to AI model optimization.
