I'm an AI Engineer at Nasdaq, building enterprise AI solutions with a strong focus on agentic systems, LLM-powered platforms, and cloud-native architectures.
My background combines Python backend engineering, applied machine learning, and production-grade AI systems designed for real-world enterprise use.
- 🤖 AI Engineer @ Nasdaq, working on an enterprise agentic AI platform that improves internal knowledge access and operational efficiency.
- 🧠 Hands-on experience with LLMs, Retrieval-Augmented Generation (RAG), and enterprise integrations such as Microsoft OneDrive and GitLab.
- 🐍 Strong background in Python backend development, building scalable services with FastAPI.
- ☁️ Experienced in deploying and operating production-ready AI systems on AWS, with a focus on reliability, scalability, and compliance.
- 📚 Continuous learner with a strong interest in applied AI, agentic systems, and practical LLM solutions.
- Design and deliver components of an enterprise-grade agentic AI platform used by internal teams.
- Build LLM-powered backend services using Python and FastAPI to support compliant, production-ready AI agents.
- Implement Retrieval-Augmented Generation (RAG) pipelines to ground AI responses in internal data sources and improve trust and adoption.
- Develop AI agents and enterprise connectors for Microsoft OneDrive and GitLab, automating document retrieval and contextual task execution.
- Collaborate within a 30-person cross-functional team to translate business needs into deployable AI capabilities.
- Support cloud-native deployments on AWS, contributing to secure and scalable system architecture.
- Designed and implemented automated UI and API testing frameworks in Python, increasing test coverage by 90%.
- Reduced testing cycles and release timelines through workflow automation and process optimization.
- Improved platform reliability and user satisfaction by identifying and resolving critical pre-release issues.
- Collaborated with cross-functional teams to deliver stable, high-quality software solutions.
- Languages: Python, SQL
- AI & ML: LLMs, Retrieval-Augmented Generation (RAG), Agentic AI Systems, Scikit-learn
- Backend: FastAPI, Flask, Django, REST APIs
- Cloud: AWS, GCP, Railway
- Data & Analytics: Pandas, NumPy, Matplotlib, Seaborn
- Visualization & BI: Plotly, Tableau / Looker Studio
- Tools: Git, Docker, Jupyter Notebook, VS Code
- 800+ hours of hands-on training in machine learning and data analytics.
- Built applied ML projects including Credit Risk Prediction and Train Accelerometry Analysis.
- Focused on real-world problem solving with data-driven approaches.
- Intensive training in Python backend development, REST APIs, and PostgreSQL.
- Built scalable web applications with a strong focus on server-side logic and data handling.
- Strong foundation in algorithms, system optimization, and engineering problem-solving.
I'm always open to discussing AI engineering, LLM systems, and practical enterprise AI solutions.
- 🏅 Kaggle
- 🥋 Codewars
- 🗿 HackerRank