I'm a Senior Software Engineer & AI Engineer with over 8 years of experience building scalable, production-grade systems and AI-driven infrastructure. I specialize in architecting high-performance backends and complex data integrations. I have a proven track record of reducing system latency by 85%, eliminating 99% of manual billing errors, and building financial platforms that process millions in transactions.

Languages & Frameworks:

AI & Data Engineering:

Databases & Vector Ops:

DevOps & Tools:

• 🔍 Conversational RAG Engine (LangChain, Pinecone, ChromaDB, OpenAI)

  • Developed a modular RAG pipeline that handles ingestion of PDFs, Docx, and live Wikipedia data.
  • Implemented Conversational Retrieval Chains with persistent memory, enabling the system to understand context and multi-turn user queries.
  • Optimized vector search using both cloud-native (Pinecone) and local (ChromaDB) stores with tiktoken cost analysis.

• ⚡ High-Performance AI Rate Limiter (FastAPI, Redis, Lua)

  • Architected a multi-dimensional rate limiter condensing 12 state checks into a single O(1) execution using Redis Lua scripts.
  • Reduced database network latency by over 85% and eliminated concurrency race conditions for 50k+ daily API requests.

• 🤖 Multi-Agent AI Framework (Python, CrewAI, LangGraph)

  • Built an orchestration framework for autonomous agent crews to solve complex tasks like financial research and engineering automation.

• 💬 AI Resume Chatbot (Python, Gradio, Pydantic)

  • Engineered an interactive "digital twin" chatbot with a self-correction mechanism to provide recruiters with real-time, conversational insights into my experience.

• Financial Systems: Owned end-to-end design of a PCI-compliant payment gateway, reducing audit costs by 80%.
• Operational Efficiency: Automated backend invoice processing that increased throughput by 80%, saving ~50 manual hours monthly.
• Infrastructure: Scaled a core platform supporting 10,000+ daily applications while reducing deployment time by 40% via CI/CD automation.
• Optimization: Reduced database query response times by 30% through advanced schema design and Django ORM optimization.
• AI Reliability: Designed fail-open LLM routing pipelines that reduced provider rate-limit violations to less than 0.1%.

I'm always open to discussing AI architecture, scalable backends, or interesting open-source projects.