</> AI Engineer | Building LLM-powered solutions | Deploying ML/LLM features to production </>
|
AI Engineer with expertise in deploying ML/LLM features, including RAG systems built with LangChain, LlamaIndex, and vector databases. Developed and fine-tuned generative AI models using QLoRA, DPO, and RLHF to enhance performance. Also delivered production-grade full-stack applications using React/TypeScript and Java/Spring Boot for high user impact. ♔ Working as AI Engineer at WERSEC Inc. |
|
|
Tech Stack: Production-grade multi-agent system using ReAct agent pattern in LangGraph's StateGraph framework, implementing three specialized LLM agents (Planner, Architect, Coder) with structured output validation via Pydantic schemas. Key Features:
|
Tech Stack: Conversational analytics platform using RAG, Llama 3.2/Mistral LLMs, and Chroma Vector DB to convert natural language into SQL queries—achieved 92% accuracy and saved 40+ analyst hours weekly. Key Features:
|
✔︎ AWS Certified AI Practitioner
✔︎ AWS Certified Machine Learning Engineer - Associate
✔︎ Microsoft Certified Python Developer (MCSD)
✔︎ Google - Introduction to AI
✔︎ Data Science with Python (Udemy)
✔︎ Basics of JavaScript (Udemy)
- Advance AI Engineering career
- Deploy 5+ production ML/LLM features
- Master advanced LLM techniques (DPO, RLHF, fine-tuning)
- Contribute to open-source AI projects (LangChain, Hugging Face)
- Build scalable RAG systems for enterprise use
- Share knowledge through technical blogs about AI/ML
Currently working on: Building production-grade LLM-powered RAG systems and fine-tuning open-source models
Learning: Advanced prompt engineering, RLHF techniques, and large-scale ML system design
Looking to collaborate on: Open-source AI projects, LLM applications, and ML infrastructure
Ask me about: RAG systems, LangChain/LlamaIndex, LLM fine-tuning, Multi-agent systems, Full-stack development
Fun fact: I've built AI systems that reduced analysis time from 3 hours to 10 seconds!