Hi, I'm Deep Rathi - AI Engineer at Key AI
I am passionate about the intersection of high-speed systems and generative AI. I thrive where code meets extreme performance, solving complex scaling problems that make machine learning truly real-time.
At a glance
Curated signals on strengths, focus areas, and how they can help.
Conducted applied AI research for autonomous driving models and data science during academic internships.
Currently specializes in optimizing generative AI models and low-latency inference systems in production environments.
Can help teams solve mission-critical performance bottlenecks in high-frequency trading and large-scale generative AI deployments.
🚀 Career trajectory
Foundational Research
Explored deep learning and computer vision fundamentals during academic internships at Binghamton University.
✦ Academic Research
✦ Computer Vision
Specialized Applied ML
Transitioned into real-time inference and low-latency environments at Remasto, focusing on production-grade generative systems.
✦ ML Engineering
✦ Production AI
System-Level AI Engineer
Currently leading efforts in AI performance optimization and robust infrastructure scaling.
✦ System Architecture
✦ Scalability
💪🏻 Superpowers
Latency Engineering Expert
Mastery of speed in distributed systems
Architected trading systems requiring microsecond-level latency performance.
Implemented high-throughput data processing using C++ and multithreading.
Reduced system bottlenecks through intensive algorithmic optimization.
Generative AI Architect
Building next-gen production models
Deploys scalable generative AI and LLM architectures.
Optimizes real-time inference workflows for production environments.
Integrates LangChain into sophisticated machine learning pipelines.
Applied Research Strategist
Translating research into technical reality
Bridged academic computer vision research to production autonomous systems.
Extracted actionable data insights from complex, noisy datasets.
Formulates robust data strategies using deep learning frameworks.
I'm excited about
Exploring collaborations on high-scale, low-latency AI infrastructure projects.
Connecting with peers to discuss advancements in real-time inference deployment.
Seeking opportunities to contribute technical expertise to cutting-edge AI startups.
I can help with
Providing technical audits for generative AI model inference latency.
Mentoring junior engineers on C++ optimization and system design.
Sharing insights on scaling production-grade machine learning pipelines.
I would love your help on
Guidance on navigating the complexities of scaling distributed AI systems.
Connections to leaders building the future of real-time trading tech.
Strategic advice on managing the growth of research-heavy engineering teams.