I am an AI and Machine Learning Engineer focused on building, evaluating, and deploying LLM-powered applications. My work spans model fine-tuning, retrieval-augmented generation, multi-agent systems, and backend engineering.
I focus on turning AI capabilities into measurable outcomes: reliable workflows, efficient asynchronous processing, and deployable services. I work across the stack, from model adaptation and agent orchestration to APIs, data systems, and cloud infrastructure.
Multi-agent workflows with LangGraph, tool integration, structured outputs, and evaluation-driven improvements.
Adapting transformer models with LoRA and QLoRA, then evaluating inference quality and output reliability.
Asynchronous Python services, FastAPI APIs, data integrations, and parallel processing pipelines.
Containerized AI applications and repeatable cloud infrastructure using AWS, Azure, Docker, and Terraform.
Built an AI product scoring and enhancement engine using parallel product and image pipelines, reducing batch processing time by 80%. Led development of an MCP-powered analytics agent with parallel tool execution, cutting query turnaround time by 55%.
Engineered EMG gesture & EEG movement detection models with optimized preprocessing pipelines, achieving production-ready signal classification across 2 real-time applications.
Won the AWS Build an Agent Challenge 2026, ranking among the Top 100. Also placed in the Top 15 at the Google Gemini 3 Hackathon 2026.
Open to AI engineering opportunities and collaborations across agentic AI, LLM applications, and production systems.