Hi, I'm Deep Rathi - AI Engineer at Key
I engineer machine learning systems focused on extreme speed and real-world application. I thrive on transforming complex AI research into robust, high-performance solutions that deliver tangible results and push boundaries.
At a glance
Curated signals on strengths, focus areas, and how they can help.
Built low-latency trading systems where every microsecond is critical.
Developing generative AI models and optimizing real-time inference.
Can help others by architecting high-speed, production-grade ML systems.
🚀 Career trajectory
Foundational ML Internships
Gained practical experience in Data Science and Machine Learning research, including work on autonomous driving models and applying AI across various domains.
✦ Data Science
✦ Research Intern
✦ Computer Vision
Low-Latency Systems Specialist
Developed expertise in building high-performance, low-latency trading systems, where precision and speed are paramount, refining skills in multithreading and optimization.
✦ Low-Latency Systems
✦ Trading Systems
✦ C++
Generative AI & Real-Time Inference
Currently focused on developing generative AI models and optimizing real-time inference for production environments, pushing the limits of speed and efficiency.
✦ Generative AI
✦ Real-Time Inference
✦ Model Optimization
💪🏻 Superpowers
Real-Time Inference Architect
Specializing in low-latency ML systems
✦ Optimizes generative AI models for swift, real-time inference.
✦ Designs systems where microseconds matter, like trading platforms.
✦ Transforms AI research into production-ready, high-speed solutions.
Generative AI Innovator
Building cutting-edge AI applications
✦ Develops advanced generative AI models from concept to deployment.
✦ Leverages LLMs and tools like LangChain for novel applications.
✦ Applies AI research across diverse domains for practical impact.
Cross-Domain AI Problem Solver
Bridging theory and practical application
✦ Experience in autonomous driving, finance, and generative AI.
✦ Combines Python, TensorFlow, and PyTorch for versatile solutions.
✦ Focuses on turning AI potential into deployed, impactful systems.
I'm excited about
✦ Connecting with pioneers in generative AI and distributed systems.
✦ Exploring collaborations on cutting-edge, high-throughput AI projects.
✦ Finding opportunities to accelerate the development of novel AI applications.
I can help with
✦ Can help teams optimize ML models for low-latency, real-time inference.
✦ Offers expertise in building robust, high-performance AI systems.
✦ Provides insights into applying generative AI for practical business needs.
I would love your help on
✦ Seeking insights into emerging trends in distributed AI infrastructure.
✦ Looking for collaborators on large-scale generative AI deployments.
✦ Interested in discussions around scaling real-time inference systems.
