Hi, I'm Deep Rathi - AI Engineer @ Key | Ex‑ML Intern @ Remasto | Low‑Latency ML & Trading Systems | Generative AI | Real‑Time Inference & Optimization
I thrive on pushing AI performance boundaries, building next-gen generative AI solutions, and creating systems that deliver immediate, measurable impact. I love tackling ambitious projects at the intersection of AI and high-performance computing.
At a glance
Curated signals on strengths, focus areas, and how they can help.
Studied Computer Science at the Vellore Institute of Technology, a top engineering institution.
Currently building and optimizing generative AI models for real-time inference at Key.
Can architect and deploy low-latency AI systems and optimize generative models for rapid inference.
🚀 Career trajectory
Foundational AI Engineering
Early experience in ML, including internships and projects focused on core algorithms and research.
✦ Machine Learning
✦ AI Research
Low-Latency Systems Specialist
Developed expertise in high-frequency trading systems and real-time inference optimization.
✦ Low-Latency Systems
✦ Trading Systems
✦ Performance Optimization
Generative AI & Real-Time Inference
Current focus on cutting-edge generative AI models and optimizing their real-time performance.
✦ Generative AI
✦ LLMs
✦ Real-Time Inference
💪🏻 Superpowers
Low-Latency ML Architect
Pioneer in building machine learning systems where speed is paramount.
✦ Expertise in optimizing inference for real-time applications, crucial for trading systems.
✦ Deep understanding of low-latency architectures, C++, and multithreading for microsecond-level performance.
✦ Proven ability to translate complex AI models into efficient, production-ready solutions.
Generative AI Innovator
Driving advancements in generative models and LLMs for practical applications.
✦ Actively developing and optimizing generative AI models with a focus on real-time inference.
✦ Skilled in leveraging tools like LangChain for sophisticated LLM applications.
✦ Experience spans across AI research and applying it to diverse, real-world challenges.
Production-Grade AI Systems
Bridging the gap between AI research and scalable, impactful deployment.
✦ Translates cutting-edge AI concepts into robust, production-grade systems.
✦ Experience with cloud platforms like AWS, ensuring scalability and reliability.
✦ Combines theoretical knowledge with hands-on implementation for tangible results.
I'm excited about
✦ Pushing the boundaries of AI performance for real-time applications.
✦ Developing next-generation generative AI solutions.
✦ Building AI systems that deliver measurable, immediate impact.
I can help with
✦ Architect and implement low-latency AI systems for high-frequency trading or real-time analytics.
✦ Optimize generative AI models for efficient and rapid inference in production environments.
✦ Develop and deploy scalable, production-grade machine learning solutions leveraging cloud infrastructure.
I would love your help on
✦ Collaborating on ambitious projects at the intersection of AI and high-performance computing.
✦ Connecting with organizations that value rapid AI innovation and deployment.
✦ Exploring opportunities to apply AI in novel, high-impact domains.
