Focus: AI/Agentic Systems, ML Platforms, Distributed Systems

I'm an engineering leader with 12+ years building production AI/ML systems, data platforms, and distributed applications at Microsoft and high-growth startups. I combine PhD-level research in Multiagent Systems with hands-on experience shipping products used by 10M+ users.

• 🏗️ Led 12-person engineering team building ML-powered operational analytics platform (10M+ utility users, $XX M cost savings)
• 🚀 Founding CTO: Built engineering org from 0→12, shipped Global Top 20 NFT platform (1M+ users, $1M+ on-chain transactions)
• 📊 Architected terabyte-scale data platform on AWS achieving 99.9% uptime with 15% infrastructure cost reduction
• 🤖 Shipped production agentic systems: Autonomous tutor, self-serving analytics agent, AI knowledge assistant

AI/ML Engineering: Generative AI (LLMs, GPT-4, Claude), ML Pipelines, MLOps, Agentic Systems, RAG, Vector Databases
Cloud Architecture: AWS (Lambda, EC2, EKS, Redshift), Azure, Microservices, Event-Driven Design, 99.9% SLA
Data Platforms: Spark, Kafka, ETL/ELT Pipelines, Terabyte-Scale Processing, Real-Time Analytics
Leadership: Team Building (0→12), Cross-Functional Collaboration, Hiring, Agile, Remote Teams

Production-grade framework for orchestrating collaborative AI agents with emergent behaviors

What it does: Enables multiple LLM agents to collaborate on complex tasks through structured communication protocols
Tech Stack: Python, LangChain, OpenAI API, AsyncIO
Why it matters: Demonstrates PhD research → production translation in cutting-edge agentic AI

Key Features:

• 🧩 Modular agent architecture with pluggable LLM backends
• 💬 Inter-agent communication with message passing
• 📊 Performance metrics and observability
• 🔄 State management for multi-turn agent interactions

Status: 🚧 Active Development | Roadmap | Docs

Semantic search engine combining OpenAI embeddings + Pinecone vector DB

What it does: Interactive search and Q&A over religious texts using retrieval-augmented generation
Tech Stack: Python, OpenAI Embeddings, Pinecone, FastAPI
Why it matters: Real-world RAG implementation with production-ready architecture

Highlights:

• ✅ Hybrid search (semantic + keyword)
• ✅ Multi-turn conversational interface
• ✅ Citation and source tracking
• ✅ Optimized chunking strategy

Python port of Resilience4j with circuit breaker, retry, rate limiting patterns

What it does: Production-grade reliability patterns for distributed systems
Tech Stack: Python, AsyncIO, Type Hints, Pytest
Why it matters: Shows understanding of production system reliability (⭐️ directly applicable to AI agent systems)

Coverage: Circuit Breaker • Retry • Rate Limiter • Bulkhead • 44% Test Coverage

Building Model Context Protocol servers to extend AI capabilities:

• geodistance - Geographic distance calculations via Google Maps API
• random-number-server - Random number generation using meteorological data

Production-grade streaming data structures:

• pyloglog - HyperLogLog for cardinality estimation
• count-min-sketch - Probabilistic frequency estimation
• correlation-logger - Production logging with request correlation

I write about engineering leadership, AI/ML systems, and production best practices at zerodowntime.dev:

Coming Soon:

• "From Research to Production: Building Multiagent Systems at Scale"
• "Cost Optimization Strategies for LLM-Powered Applications"
• "Architecting Fault-Tolerant Agentic Systems"

PhD in Computer Science (Multiagent Systems) - University of Nebraska-Lincoln
Publications: AAAI, AAMAS, IEEE Transactions on Cybernetics
Awards: Top 20 AI Applications (AAAI), Othmer Fellowship

• 🏢 NISC - Engineering Team Lead, Operational Analytics (2024-Present)
• 👔 LiquidX Studio - Chief Technology Officer (2022-2024)
• 💼 Shohoz - VP of Technology (2019-2021)
• 💻 Microsoft - Senior SDE, Office 365 Data Loss Prevention (2013-2019)

I'm actively exploring Lead Engineer and Engineering Manager roles in AI/Agentic Systems.

Open to:

• Technical Architecture & System Design discussions
• Multiagent Systems & LLM Agent architectures
• Engineering leadership opportunities (team building, mentorship)
• Speaking engagements on AI/ML production systems

📧 Email: nobel@outlook.com
💼 LinkedIn: linkedin.com/in/nobelkhandaker
📝 Blog: zerodowntime.dev

"Designing the future, one distributed system and AI agent at a time."

• 🚀 Expanding Artemis with advanced agent coordination patterns
• 📚 Building production-grade RAG frameworks
• 🛠️ Creating engineering leadership resources
• ✍️ Technical blog series on agentic AI systems