AI Engineer
Yiğit Can Özdemir
Building AI systems that work in the real world.
Services
What I Offer
RAG & LLM Systems
Production-ready retrieval and LLM workflows designed to behave predictably, scale reliably, and support real operational use.
- RAG pipelines using Redis, PostgreSQL & pgvector
- Agentic, multi-step workflows with structured orchestration
- Custom evaluation and observability for LLM behavior
- LLM orchestration for internal tools and automation
Agentic Automation
Agent systems that coordinate LLM calls, tools, APIs, and business logic with deterministic guardrails for reliable automation.
- Multi-LLM orchestration with fallbacks
- Tool-using agent architectures
- Task routing, memory, and workflow management
- Error-handled, production-safe execution layers
Backend & API Engineering
Fast, stable backend services engineered for AI workloads and built to run reliably in production.
- FastAPI microservices for AI and automation
- LLM-serving and orchestration endpoints
- Authentication, rate limiting, and monitoring
- AWS-ready Dockerized deployments
Frontend Development
Modern Next.js interfaces for AI products, dashboards, and internal tools.
- Next.js dashboards and admin panels
- Full-stack AI application delivery
- API integration with LLM/RAG services
- Responsive UI with smooth UX
AI / ML Development
ML models and pipelines built for real-world conditions using solid engineering and validation practices.
- Predictive modeling (regression, classification, LSTM)
- Computer vision tools using OpenCV
- Real-world data preprocessing and cleaning
- Deployment-ready ML pipelines
Cloud Deployment
Production deployments designed for stability, observability, and smooth scaling.
- AWS deployment with Docker
- Container orchestration and environment setup
- Load balancing and performance tuning
- CI/CD workflows with GitHub Actions
My Projects
AI Customer Support Assistant
Production-ready AI assistant handling product discovery, FAQ resolution, order tracking, and store logic via real-time WebSocket communication. Supports 4+ concurrent tool-calling agents, vector search across product catalogues, and full observability via Grafana dashboards.
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.
Düzkır Lojistik – Corporate Web Platform
A full-featured corporate website for a Turkish heavy-load logistics company operating across 13 countries. Includes a custom CMS panel with AI-powered automatic translation, a quote request ticketing system with automated email notifications, a newsletter system, and media storage on Cloudflare R2. Integrated interactive route maps and Google Analytics.
Scrapyard ERP – Business Management System
Custom desktop ERP for a local scrapyard. Replaced a fully paper-based workflow that made it hard to track real profit, cash flow, and inventory. Now the client tracks materials, weights, expenses, and daily balance in one place. Used in daily operations since launch.
My Skills
Core Expertise
Additional Skills
Experience
Freelance AI Engineer
Self-employed
Nov 2025 - Present
Remote
- Designed and delivered production-ready RAG pipelines using Redis, PostgreSQL, and pgvector, serving real-time semantic search across multi-thousand document corpora
- Built multi-agent agentic workflows orchestrating 4+ LLMs (OpenAI, Claude, and local models) within a single backend system, reducing manual task handling to zero for targeted workflows
- Architected FastAPI-based microservices handling concurrent AI workloads with sub-second response latency under normal load
- Containerized and deployed applications on AWS using Docker, integrating Grafana and Prometheus for full observability across all services
- Shipped 3+ end-to-end products covering AI backend, deployment, and Next.js frontend within solo engagements
- Engineered deterministic system behavior to ensure reliability and maintainability long after delivery
AI Engineer – Finalist (Competition)
TEKNOFEST – AI in Transportation Competition
Nov 2022 - May 2023
Istanbul, Turkey
- Ranked 17th out of 32 finalist teams in TEKNOFEST 2023, a nationwide AI competition with hundreds of applicants across Turkey
- Built a real-time YOLO-based object detection pipeline classifying 6+ vehicle categories from drone imagery with live inference
- Implemented UAV ambulance landing zone feasibility logic using spatial constraints and multi-class detection outputs
- Integrated model with official competition APIs for real-time evaluation across multiple qualification stages
- Awarded Honourable Mention — the only solo, high-school-level participant competing among university teams
AI Engineer
Toscelik Profil & Sac
Sep 2022 - Feb 2024
Osmaniye, Turkey
- Engineered predictive maintenance models (TensorFlow regression & LSTM) across 7 rolling mill motors and 20 vibration sensors, achieving ~89% fault detection accuracy
- Reduced unplanned maintenance response time by enabling early fault detection on 3 months of historical time-series data
- Built and deployed a Flask-based monitoring dashboard visualising real-time machine predictions vs. actual sensor performance
- Designed OpenCV-based steel width measurement tooling used in daily production-line quality control
- Collaborated directly with production engineers to validate model outputs against real operational constraints
Testimonials
Yiğit built our entire corporate platform from the ground up. CMS, quote system, automated emails, AI translation, everything. The quality was well beyond what we expected. He took the time to really understand our business and made sure the solution fit how we actually operate, not just what we asked for.
Furkan Ellek
Head of Operations · Düzkır Lojistik
We needed a system that fit exactly how we work. Tracking materials, weights, expenses, and daily cash flow all in one place. Yiğit built it to our needs and we have been using it every day since. It has made running the business a lot easier.
S. Kılıç
Business Owner · Local Scrapyard
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.
Get In Touch
Let’s talk about how AI can power your business and help you build systems that work in the real world
Send a Message
Connect With Me
Choose the channel that suits you
Location & Phone
Let’s sync details when you’re ready