Building production-grade AI systems — from LLMs and RAG pipelines to MLOps and autonomous agents. Transforming data into intelligent solutions.
I'm a Machine Learning Engineer and AI Specialist with hands-on experience building end-to-end intelligent systems. Currently at BNY Mellon and pursuing advanced study at Illinois Institute of Technology.
From Retrieval-Augmented Generation pipelines to autonomous AI agents, I specialize in taking ML from research to production — multimodal platforms, LLM fine-tuning, and scalable MLOps at real scale.
Currently deep-diving into Agentic AI frameworks and building SummarAIze — a multimodal news intelligence platform.
A curated stack of tools I wield to build production AI systems.
Multimodal news platform generating real-time AI summaries. Processes text, images, a…
Privacy-first conversational AI on local hardware. Custom RAG pipeline with persisten…
Real-time food recognition & nutritional analysis. 94% accuracy across 101 food categ…
Production ML monitoring with real-time drift detection, performance tracking, and au…
Scalable document Q&A with multi-document ingestion, semantic chunking, and reranking…
End-to-end GenAI on AWS using Bedrock, SageMaker & Lambda. Automated training, evalua…
End-to-end AI solutions tailored to your business. Prototype to production.
LLMs at production scale
Build production-ready LLM applications with RAG, fine-tuning, and multi-agent architectures that actually work in the real world.
From architecture design to deployment, I handle the full GenAI lifecycle — evaluation, safety guardrails, cost optimization, and monitoring.
Research → production
End-to-end ML from data preprocessing to model deployment and monitoring. Specializing in predictive analytics and computer vision.
I follow rigorous experiment tracking, hyperparameter optimization, and model interpretability practices to deliver models that generalize.
AWS-native pipelines
Production AWS deployment with CI/CD, monitoring, and auto-scaling. SageMaker, Bedrock, Lambda — end-to-end.
Infrastructure as code, blue-green deployments, A/B testing, and automated rollbacks — your ML systems run reliably at scale.
Intelligent workflows
Intelligent conversational AI integrated with your existing workflows and data. From customer service to internal automation.
Built with reliability in mind — fallback handling, human escalation paths, analytics dashboards, and continuous improvement loops.
Insight to action
Raw data to actionable intelligence with advanced analytics, time series forecasting, and interactive dashboards.
I deliver clear narratives alongside technical deliverables — every insight comes with recommended actions and implementation paths.
High-throughput inference
High-performance AI-powered REST APIs built with FastAPI, optimized for scale, reliability, and low latency.
Async-first, horizontally scalable APIs with comprehensive observability — tracing, metrics, and alerting baked in from day one.
Not sure which service fits your needs?
Book a free consultation →Whether you need a production ML system, GenAI application, or expert consultation — I'm here to turn your AI vision into reality.