Hi, I'm Deep Rathi - AI Engineer at Key
I am obsessed with the intersection of complex machine learning research and extreme performance. I thrive in high-stakes environments where every millisecond counts, turning raw algorithms into robust systems.
At a glance
Curated signals on strengths, focus areas, and how they can help.
Conducted foundational applied research on autonomous driving models and complex data science early in their professional career.
Engineers low-latency inference pipelines and production-grade generative AI systems at the cutting edge of machine learning.
Provides expert technical mentorship on C++ performance, multithreading, and optimizing deep learning models for production scale.
🚀 Career trajectory
Research Foundations
Explored foundational ML and data science in academic and research settings.
✦ Researcher
✦ Academic Background
Production Engineering
Transitioned to building real-world inference systems and optimizing neural models.
✦ Systems Engineer
✦ ML Specialist
Strategic Optimization
Currently focusing on scaling Generative AI and low-latency performance at scale.
✦ AI Engineer
✦ Optimization Lead
💪🏻 Superpowers
Architect of Microsecond Precision
Engineering performance-critical systems at the edge of latency limits.
✦ Optimized inference pipelines for high-throughput, low-latency environments.
✦ Leveraged C++ and multithreading to solve complex computational bottlenecks.
Applied AI Innovation
Bridging research prototypes with production-grade engineering realities.
✦ Deploying LLMs and generative models within real-time production frameworks.
✦ Refining machine learning models for maximum efficiency in deployment.
Technical Research Integration
Translating data science theory into robust, scalable infrastructure.
✦ Synthesized research insights for autonomous systems and predictive modeling.
✦ Utilized rigorous data analytics to drive strategic system architecture decisions.
I'm excited about
✦ Discovering new communities of AI practitioners to exchange deployment best practices.
✦ Finding opportunities to contribute to high-impact, open-source infrastructure projects.
✦ Connecting with technical leaders to explore future trends in production-grade machine learning.
I can help with
✦ Mentoring developers on optimizing Python and C++ for low-latency machine learning tasks.
✦ Reviewing architectural patterns for deploying generative AI in resource-constrained environments.
✦ Sharing technical insights on scaling real-time inference pipelines in cloud-native settings.
I would love your help on
✦ Learning about emerging strategies for maintaining data consistency in distributed AI systems.
✦ Gaining perspective on the operational challenges of managing large-scale LLM inference costs.
✦ Exploring new networking opportunities within the specialized niche of algorithmic trading systems.
