I’m a software engineer with over 7 years of experience in building scalable back-end systems, cloud-native applications and automation in the AWS ecosystem. I combine strong Python development expertise with a focus on infrastructure, DevOps and generative AI to deliver modern, intelligent solutions.

Languages & Frameworks
🐍 Python (FastAPI, Django, Flask) • ☕ Java (Spring Boot) • 🐹 Go (basic)
🧩 RESTful APIs • GraphQL • Async I/O • Event-driven systems

Cloud & DevOps
☁️ AWS (EC2, S3, Lambda, CloudFormation, RDS, ECS, IAM)
🐳 Docker • 🧭 Kubernetes • 🧱 Helm • 🔧 Terraform • 🧰 CI/CD (GitHub Actions, Jenkins)

Databases & Storage
🗄️ PostgreSQL • MySQL • DynamoDB • Redis • S3 • JSONB query design

AI, Machine Learning & Generative AI
🧠 Machine Learning: Scikit-learn • XGBoost • TensorFlow • PyTorch
🧩 Generative AI: OpenAI API • Hugging Face Transformers • LangChain • LlamaIndex
🗃️ RAG (Retrieval-Augmented Generation) pipelines with vector databases (FAISS, Pinecone)
🪄 Prompt Engineering & Agent Design (OpenAI Assistants, Ollama, LangChain Agents)
🧰 MLOps: Model serving with FastAPI, model lifecycle management with MLflow & AWS SageMaker
🧮 Synthetic Data Generation for model training & simulation pipelines
🧑‍💻 Integrating LLMs into cloud workflows — serverless inference, monitoring & fine-tuning
⚙️ Responsible AI: Explainability, data privacy, and model governance

Tools & Platforms
🧩 Git • VS Code • Linux (Ubuntu, CentOS) • F5 Networks (LTM/GTM) • AppViewX
📊 Monitoring: CloudWatch, Prometheus, Grafana

As generative AI (GenAI) continues to reshape how systems are built and deployed, I leverage this domain to extend my backend/cloud expertise into smarter, more autonomous solutions.

• Integrating LLMs into backend APIs for real-time data enrichment and automation
• Building RAG systems to connect enterprise data with language models
• Deploying AI models on AWS using SageMaker endpoints and Lambda functions
• Experimenting with multi-agent orchestration for DevOps automation and knowledge retrieval
• Exploring synthetic data generation for domain-specific ML training
• Evaluating LLM platforms (OpenAI, Anthropic Claude, Mistral, and Ollama) for hybrid cloud environments

Why this matters:
Generative AI isn’t just a tool for “content” — it’s becoming a core part of enterprise systems for automation, augmentation and intelligent operations. With my cloud/infrastructure background, I’m uniquely positioned to bridge between “model building” and “production infrastructure” in the GenAI era.

A Django-based service to automate VIP provisioning for F5 LTM/GTM, certificate management and DDI integration.

• Implemented async VIP creation with request-polling and state-tracking.
• Secure API integration via Okta bearer-tokens.
• Logging with Log4j + dynamic alerting.
• End-to-end integration tests improved reliability.

Designed and executed hybrid cloud strategy for manufacturing-control workloads.

• Migrated legacy DCS workloads into AWS IaaS + PaaS with governance, risk & cost-management.
• Used infra-as-code templates, Mermaid diagrams for architecture documentation.

Developed proof-of-concept models for demand forecasting / churn prediction using Python (Pandas, scikit-learn) and cloud infrastructure.

• Explored GenAI for model explanation and synthetic-data augmentation.
• Evaluated ML platforms (Google AI, Azure ML, IBM Watson) and embedded cloud workflows for MLOps.

• Cloud-native architecture & serverless patterns
• DevOps, Infrastructure-as-Code & GitOps
• Generative AI, MLOps and multimodal systems
• Hybrid workloads (IaaS + PaaS + SaaS)
• Distributed computing, microservices & event-driven systems
• Tennis / hiking / mystery-novels

🎓 Master of Science in Computer Science from Syracuse University Focus: Cloud Computing • Distributed Systems • Artificial Intelligence

“Building scalable systems isn’t just about code — it’s about clarity, reliability, and intelligent augmentation.”