Featured Work

Highlighted projects and initiatives demonstrating my expertise in AI engineering and leadership.

RAG Platform Development

AI Infrastructure

Led the development of a comprehensive RAG (Retrieval-Augmented Generation) platform that powers Asana's LLM features. Working with my talented team, I helped pivot from a single-product approach to a multi-product platform supporting four distinct features, resulting in a 15x increase in system traffic.

  • Advanced vector search capabilities
  • Context-aware document retrieval
  • Cross-application integration framework
  • Improved p95 performance of onboarded features by an average of 54%
RAG LLMs Vector DB Performance

AI Evaluation System

Quality Assurance

Developed and led Asana's large language model testing and evaluation program, creating a comprehensive framework for ensuring AI feature quality and reliability.

  • Automated evaluation suite
  • Quality metrics and benchmarking
  • Pre-release model testing
  • Strategic partnerships with Anthropic and OpenAI
Evaluation LLMs QA Benchmarking

Agentic Context Management

Performance Optimization

Led development of innovative techniques for managing context in agentic AI systems, significantly improving both performance and quality while reducing operational costs.

  • 24% improved time to first token
  • Enhanced evaluation pass rate from 92% to 96%
  • 32% LLM budget reduction
  • Context optimization algorithms
Agentic AI Performance Cost Optimization Context Management

ML Recommendation System

Machine Learning

Implemented a recommendation system for product merchandising that drove significant business growth and improved user engagement metrics.

  • 25%+ increase in primary conversion rate
  • Personalized recommendation algorithms
  • User behavior analysis
  • A/B testing framework
ML Recommendations Conversion Product

Bit Vector Algorithm

Performance Engineering

Designed and implemented a custom bit vector-based algorithm that achieved a 1000x performance improvement for critical filtering and sorting operations.

  • Reduced processing time from 7s to 7ms
  • Optimized memory usage
  • Scaled to handle large datasets
  • Improved user experience
Algorithms Performance Optimization Scalability

Third-Party Integrations Framework

System Architecture

Expanded Asana's RAG capabilities into third-party applications, creating a flexible integration framework that connects with various external data sources.

  • Google Drive integration
  • OneDrive connectivity
  • Amazon Q integration
Integrations API Design Data Connectors Architecture