Portfolio

Featured Projects

Showcasing work in AI/ML, platform architecture, and scalable systems that create real business impact.

First-to-Market Gen AI Analytics Platform
Featured
Product Innovation
Developed and launched the first gen AI powered chat-based analytics across all XM (experience management) products before competitors, resulting in winning Emirates Airlines.

Challenge

XM platforms needed intelligent, conversational interfaces for analytics. Competitors like Qualtrics, QuestionPro, and Medallia were racing to build similar capabilities, creating a critical time-to-market challenge.

Solution

Built and shipped a production-ready gen AI powered chat assistant using LLMs, RAG architecture, and deep XM domain integration. Achieved market leadership through rapid iteration and customer-centric design.

Impact & Results

  • ✓First to market before Qualtrics, QuestionPro, and Medallia
  • ✓Won and onboarded Emirates Airlines as enterprise customer
  • ✓Established competitive differentiation in the XM space
  • ✓Reduced time-to-insight for analytics users by 70%
  • ✓Enabled non-technical users to perform complex analysis

Technologies Used

Gen AILLMRAGOpenAIClaudePythonXM PlatformPostgreSQL
OpenAI Evals Contribution
Featured
Open Source
Contributed to OpenAI's evaluation framework, helping improve AI model assessment methodologies and testing practices.

Challenge

AI models need robust evaluation frameworks to measure performance, accuracy, and safety across diverse scenarios. The community lacked standardized evaluation methodologies.

Solution

Developed evaluation scripts and test cases for the OpenAI Evals project, contributing to the open-source community's ability to assess LLM capabilities with standardized benchmarks.

Impact & Results

  • ✓Recognized by OpenAI for valuable contributions
  • ✓Helped improve evaluation methodologies for AI models
  • ✓Contributed to open-source AI/ML ecosystem
  • ✓Enabled better benchmarking across the industry

Technologies Used

PythonOpenAI APILLMAI EvaluationTestingOpen Source
AI Platform Layer at HappyFox
Featured
Platform Engineering
Created the foundational AI platform layer at HappyFox, enabling intelligent automation and AI-powered features across the entire product suite.

Challenge

HappyFox needed to integrate AI capabilities across multiple products (Help Desk, Chat, BI) without creating technical debt or fragmenting the architecture.

Solution

Designed and built a centralized AI platform layer providing reusable AI services, model management, and intelligent automation capabilities that all products could leverage.

Impact & Results

  • ✓Enabled AI features across entire HappyFox product suite
  • ✓Created reusable AI infrastructure reducing time-to-market
  • ✓Standardized AI/ML practices across engineering teams
  • ✓Improved product capabilities with intelligent automation
  • ✓Established foundation for future AI innovations

Technologies Used

AI PlatformPythonAWSLLMPlatform EngineeringMicroservicesSaaS
100x Scale Architecture Transformation
Featured
Leadership & Architecture
Revamped the architecture at Xebo to handle loads beyond 100x the current size while scaling the engineering team from 8 to 35 members.

Challenge

Xebo's legacy architecture couldn't scale to meet growth projections. Simultaneously needed to scale the engineering team 4x while maintaining velocity and quality.

Solution

Led comprehensive architectural transformation to microservices with event-driven design. Built engineering culture, hired and mentored team members, and established scalable processes.

Impact & Results

  • ✓Scaled system architecture to handle 100x current load
  • ✓Grew engineering team from 8 to 35 members
  • ✓Improved system reliability to 99.9% uptime
  • ✓Reduced deployment time from hours to minutes
  • ✓Enabled independent team autonomy and velocity
  • ✓Decreased infrastructure costs by 40%

Technologies Used

MicroservicesKafkaAWSDockerKubernetesPythonTeam LeadershipScalability