Resume

Nous Research

Building and maintaining Hermes Agent, an intelligent AI assistant with tool-use, skills, and multi-agent orchestration capabilities.

• Architected the agent runtime with support for dynamic tool loading and skill-based workflows
• Implemented multi-provider LLM routing with fallback and retry logic
• Designed the skills system for reusable, composable procedural knowledge
• Built automated evaluation pipelines for measuring agent performance

Previous Company

Led the development of production LLM inference pipelines and AI-powered products.

• Deployed and scaled vLLM inference servers serving millions of requests per day
• Built RAG pipelines using vector databases and embedding models
• Developed internal tools for prompt engineering and model evaluation
• Reduced inference latency by 60% through optimized batching and quantization

Earlier Company

Full-stack development with a focus on backend systems and data pipelines.

• Designed and implemented microservices architecture on Kubernetes
• Built real-time data processing pipelines with Kafka and Flink
• Migrated legacy monolith to modular service-oriented architecture

AWS Solutions Architect — Professional

Amazon Web Services

2023

Google Cloud Professional Data Engineer

Google Cloud

2022

Kubernetes Administrator (CKA)

CNCF

2022

• Focus on machine learning and distributed systems
• Dean's List, Graduated with honors