Professional Overview
I design and build production AI systems end to end, covering architecture, backend and deployment. My main areas are voice AI, RAG/LLM applications, computer vision and edge inference. I mostly use Python and C++, OpenAI and open-source LLMs served with vLLM, VLMs, Twilio, AWS, Palantir Foundry, and TensorRT/OpenVINO/ONNX for edge models. I also use agentic coding tools like Claude Code every day to ship faster. One project: I built a real-time voice AI agent on Twilio Conversational Relay that handles English and Turkish callers. It took over routine inbound calls that staff used to answer by hand, so callers get instant answers around the clock. I focused on cutting response latency so conversations feel natural rather than robotic.
Experience
Employment Type
Areas of Expertise
AI & Machine Learning Engineers
Design, train, and ship production ML models — from data pipelines to model inference at scale. Covers supervised learning, neural networks, LLM integration, and model optimisation.
NLP & Prompt Engineering
Build natural language processing systems, fine-tune large language models, and craft reliable production prompts for AI-powered products.
Computer Vision
Develop image recognition, object detection, video analysis, and multimodal AI systems for real-world applications.
