About Me
I help startups and businesses turn their AI ideas into reliable, production-ready systems. My work focuses on practical, real-world implementation using RAG pipelines, LLM orchestration and agentic workflows that support real users and daily operations.
In recent projects, I’ve built retrieval systems with PostgreSQL, Redis and pgvector, orchestrated LLMs such as OpenAI, Claude and open-source models within backend logic, developed FastAPI microservices, deployed applications on AWS with Docker, and created clean interfaces using Next.js for end-to-end delivery.
Before freelancing, I worked as an AI Engineer in industrial automation, developing predictive maintenance models, computer vision tools and monitoring dashboards for steel production lines. Working in this environment taught me how to design AI systems that stay stable under noisy data, strict uptime requirements and real operational constraints.
My approach is simple: use LLMs where they bring real value, keep system logic deterministic and observable, and ensure everything remains maintainable long after deployment.
If you’re a business looking to bring AI into real operations, I’d be glad to talk. We can explore your challenges and see how RAG systems, LLMs or agentic workflows could help move your business forward.
Experience
Freelance AI Engineer
Self-employed
- Designed and delivered production-ready RAG pipelines using Redis, PostgreSQL, and pgvector
- Built multi-step agentic workflows and orchestrated LLMs (OpenAI, Claude, and local models) within backend systems
- Developed FastAPI-based microservices and orchestration layers for AI-powered automation
- Containerized and deployed applications on AWS using Docker with strong observability and monitoring practices
- Created lightweight, functional Next.js interfaces for internal tools and end-to-end product delivery
- Engineered deterministic, maintainable system behavior to ensure reliability in real-world environments
AI Engineer – Finalist (Competition)
TEKNOFEST – AI in Transportation Competition
- Finalist in the TEKNOFEST 2023 Artificial Intelligence in Transportation challenge, a nationwide AI competition focused on aerial image analysis for next-generation transportation systems
- Built a real-time YOLO-based object detection pipeline for classifying multiple vehicle categories from drone imagery (land, marine, rail, UAV-related)
- Implemented logic to assess UAV ambulance landing zone feasibility using detected objects and spatial constraints
- Integrated the model with official competition APIs for real-time inference and scenario evaluation
- Advanced through multiple qualification stages and ranked 17th among 32 finalist teams nationwide
- Awarded Honorable Mention and competed as the only solo high-school-level participant among university-level teams
AI Engineer
Tosçelik Profil ve Sac
- Developed predictive maintenance models using TensorFlow (regression & LSTM) on vibration and time-series sensor data
- Built and deployed a Flask-based dashboard to visualize machine predictions vs actual performance
- Created OpenCV-based steel width measurement tooling for production-line monitoring and quality control
- Implemented deep learning pipelines using TensorFlow and Python for operational use cases in the rolling mill
- Collaborated closely with production engineers to validate results and align solutions with real-world operational constraints
Technical Skills
Core
Additional
Featured Projects
E-Commerce AI Agent
An AI assistant that helps customers find products, answer FAQs, check orders and handle store logic. Built as a reliable, production-ready AI system for online businesses.
CineSearch – Semantic Title Search Engine
A semantic search engine built on 500k cleaned IMDb entries using Qwen embeddings, OpenAI intent parsing and a multi-step ranking pipeline. It understands user preferences such as genre, theme, tone and region to return the most relevant titles.