class MLOpsEngineer:
    def __init__(self):
        self.name = "Li-Yu Chu"
        self.role = "MLOps Engineer"
        self.location = "Vancouver, BC 🇨🇦"
        self.experience = "2+ years production ML infrastructure"
        
        self.core_skills = [
            "Serverless ML Inference (<100ms latency)",
            "Distributed Systems & Fault Tolerance",
            "Infrastructure as Code (Terraform)",
            "Production AWS Architecture"
        ]
        
        self.certifications = [
            "✅ AWS Solutions Architect Associate",
            "✅ HashiCorp Terraform Associate"
        ]
    
    def current_focus(self):
        return [
            "Building end-to-end MLOps pipelines",
            "Optimizing model serving infrastructure",
            "Implementing production monitoring systems"
        ]
    
    def say_hi(self):
        print("🚀 Building scalable ML infrastructure that powers real-world applications!")

engineer = MLOpsEngineer()
engineer.say_hi()

Why work with me?

• ✅ 2+ years building production ML systems at scale
• ✅ Live projects with measurable impact (<100ms inference, $0 hosting costs)
• ✅ Strong foundation in distributed systems and cloud architecture
• ✅ Full-stack MLOps: from training orchestration to model monitoring

Live Demo: luichu.dev | Production-grade MLOps showcase

Highlights:

• 📊 Comprehensive portfolio demonstrating end-to-end ML infrastructure
• 🎯 Real production systems with quantifiable metrics
• 📈 Cost-optimized architecture ($0/month hosting)
• 🔧 Multi-environment setup with CI/CD automation

Impact: Portfolio designed to pass technical and HR interviews for MLOps roles

Production AWS Lambda architecture for ML model serving

MLOps Features:

• 🚀 Sub-100ms latency - Optimized for real-time inference
• 📈 Auto-scaling - 0 to 1000+ req/s with no manual intervention
• 💰 Cost-optimized - 90% cheaper than traditional EC2 hosting
• 🔒 Enterprise security - WAF, IAM, JWT authentication
• 📊 Full observability - CloudWatch metrics, dashboards, alerts

Tech Stack: AWS Lambda, DynamoDB, Terraform, TypeScript, API Gateway
Use Cases: Model serving APIs, feature stores, real-time predictions

Fault-tolerant job queue for mission-critical workloads

Production Features:

• 💾 Zero data loss - Write-Ahead Log ensures durability
• ⚡ High throughput - 250+ jobs/second with concurrent processing
• 🛡️ Crash recovery - Sub-3s recovery time with snapshots
• 🔧 Raft consensus - Distributed coordination and leader election
• 📊 Prometheus metrics - Production monitoring built-in

Tech Stack: Go, Raft Consensus, Write-Ahead Log, Distributed Systems
Use Cases: ML training orchestration, ETL pipelines, batch processing

MLOps Expertise:

• 🎯 Model serving & deployment (Lambda, SageMaker, custom APIs)
• 📊 Experiment tracking (MLflow, DVC, model registry)
• 🔄 CI/CD pipelines (GitHub Actions, automated testing)
• 📈 Monitoring & observability (CloudWatch, Prometheus, drift detection)
• 💰 Cost optimization (serverless, right-sizing, budget alerts)

Cloud Services:

• ☁️ AWS: Lambda, DynamoDB, S3, SageMaker, CloudWatch, Step Functions
• 🏗️ IaC: Terraform (multi-env), CloudFormation
• 🔐 Security: IAM, WAF, Secrets Manager, KMS

🏢 Software Engineer @ HiTrust, Inc. (Jan 2023 – Dec 2024)

• Developed secure microservices handling millions of financial requests
• Optimized data pipelines → 30% performance improvement
• Managed Kubernetes deployments for production services
• Implemented monitoring infrastructure with comprehensive logging

🔬 Product Planner (Data & ML) @ Astra Technology (Oct 2018 – Dec 2019)

• Built time-series prediction models using Python stack
• Led Computer Vision PoC in collaboration with NTT Japan
• Defined technical requirements for ML model production deployment

🎓 Master of Science - Applied Computer Science
Fairleigh Dickinson University (2025-2027)
Focus: Artificial Intelligence, Advanced Operating Systems, Systems Programming

🏆 Professional Certifications

• ☁️ AWS Certified Solutions Architect – Associate
• 🏗️ HashiCorp Terraform Associate

📚 Specialized Training

• Big Data Analytics Bootcamp - Institute for Information Industry (2017-2018)
• Focus: Data analytics, machine learning, big data technologies

• 🚀 Advanced model monitoring and drift detection algorithms
• 📊 MLflow & DVC for complete ML lifecycle management
• ☁️ AWS SageMaker for enterprise ML at scale
• 🗄️ Feature stores and data versioning best practices
• 🔧 Kubeflow and ML on Kubernetes

I'm actively seeking MLOps Engineer and ML Infrastructure Engineer roles where I can:

📧 Email: liyu.chu.work@gmail.com
🔗 Portfolio: luichu.dev
💼 LinkedIn: linkedin.com/in/chuliyu
📍 Location: Vancouver, BC, Canada 🇨🇦