AI/ML & Python Engineer | LLM Evaluation, RAG, FastAPI, AWS
I am a software and AI/ML engineer with 9 years of experience building backend systems, cloud-native applications, and production AI solutions. I specialize in Python, FastAPI, Django, LLM evaluation, prompt engineering, retrieval-augmented generation (RAG), and MLOps. I build reliable AI systems including multi-agent workflows with LangGraph, secure RAG applications, REST APIs, and model integrations across AWS, Azure, Google Cloud, Vertex AI, and AWS Bedrock. I have experience working in security- and compliance-focused cloud environments, including AWS GovCloud and Azure IL5+. I also design AI evaluation pipelines and benchmark tasks for coding agents. My work includes automated pytest suites, LLM-as-a-judge grading workflows, rubric calibration, FastAPI/SQLAlchemy test fixtures, JWT authentication testing, and cloud CI validation. I focus on creating realistic evaluation scenarios that produce meaningful and fair model-performance signals. Beyond AI, I have delivered full-stack products with React, Next.js, TypeScript, Elixir, RabbitMQ, WebSockets, SQL, OAuth, RBAC, analytics dashboards, and offline-first capabilities. I collaborate effectively with product, security, and engineering teams and communicate technical decisions clearly through documentation.
AI Benchmark Author / Evaluation, Grader-Pipeline Engineer at Mindrift (Dec 2025 - Present) AI/ML Engineer (Contract/Freelancer) at Mindrift (Mar 2025 - Dec 2025) Python Developer at LIAPP Remote (Jan 2022 - Jan 2025)