Hi, I'm Deep Rathi - AI Engineer at Key
I am fueled by the challenge of turning complex data into intuitive, living AI systems. I thrive in fast-paced teams where we can push boundaries, solve abstract problems, and build tech that truly matters.
At a glance
Curated signals on strengths, focus areas, and how they can help.
Developed robust machine learning pipelines while working at high-growth engineering environments.
Currently building cutting-edge AI systems and scalable automation tools as an AI Engineer at Key.
Offers deep technical mentorship on model architecture and practical strategies for deploying agentic AI systems.
🚀 Career trajectory
Foundational Research
Explored autonomous driving and AI research at Binghamton University.
✦ Research
✦ Computer Vision
Practical Scaling
Focused on real-time inference and system optimization at Remasto.
✦ ML Engineering
✦ Optimization
System Architecture
Building high-performance AI systems at Key to solve real-world problems.
✦ AI Engineer
✦ Systems Design
💪🏻 Superpowers
Latency Engineering
Mastery of millisecond-sensitive performance optimization
✦ Architects high-throughput systems with minimal execution overhead.
✦ Implements optimized threading models for real-time data processing.
Generative AI Integration
Deploying scalable LLMs in production environments
✦ Develops efficient pipelines for production-grade generative models.
✦ Refines model inference speed using advanced optimization techniques.
Algorithmic Research
Applying data-driven insights to complex system architectures
✦ Leverages deep learning and statistics for robust predictive modeling.
✦ Conducts rigorous data analysis to refine system decision-making.
I'm excited about
✦ Exploring advanced architectural patterns for next-generation AI models.
✦ Connecting with experts in high-frequency trading and performance computing.
✦ Identifying collaborative opportunities to push the limits of real-time inference.
I can help with
✦ Providing technical audits for latency-sensitive machine learning pipelines.
✦ Mentoring developers on C++ optimization for high-performance systems.
✦ Sharing insights on scaling generative AI in production environments.
I would love your help on
✦ Guidance on navigating the complexities of large-scale system integration.
✦ Peer feedback on architectural decisions for real-time ML deployment.
✦ Networking with domain experts in low-latency infrastructure design.