AI / LLM Engineer

TEB; Fatih; On-site; TRY 167,000 - 257,000; Full time

Job summary

TEB is seeking a talented AI/LLM Engineer with 1–2 years of hands-on experience to join our team and help build AI-powered features across our projects. You will work on integrating LLMs into existing architectures and contribute to product discovery and delivery.

Strong focus on UI and backend collaboration, experience with vector databases, Python, and model deployment. You will design, develop, and optimize RAG pipelines, embeddings, indexing, and prompt strategies while staying abreast of

Qualifications

• 1–2 years of hands-on AI/LLM development experience.
• Bachelor’s or Master’s degree in Artificial Intelligence Engineering or Computer Engineering.
• Proficient in Python.
• Experience with vector databases and embeddings.
• Experience designing and evaluating RAG systems.
• Good communication and team-oriented mindset.

Responsibilities

• Design, develop, and deploy AI/LLM-powered features for new projects.
• Build, optimize, and maintain RAG pipelines connecting LLMs with data sources.
• Integrate AI models into front-end (UI) and back-end systems.
• Collaborate with cross-functional teams to define project requirements.
• Optimize model performance, prompts, and data pipelines.
• Implement and manage data chunking, embeddings, and indexing for semantic search.
• Stay up-to-date with advances in AI, LLMs, and software engineering practices.

Skills

AI development

LLM development

UI development

Backend development

Python

LangChain

Langgraph

Vector databases

Education

Bachelor’s or Master’s in Artificial Intelligence Engineering

Bachelor’s or Master’s in Computer Engineering

Tools

Pinecone

Qdrant

Milvus

Chroma

pgvector

Job description

We are looking for a talented and motivated AI / LLM Engineer with minimum 1-2 years of experience to join our team. In this role, you will play a key part in developing and integrating artificial intelligence and Large Language Model (LLM) technologies into our newly developed projects.

The ideal candidate will not only possess a solid foundation in AI but also have a strong understanding of UI and Backend development to ensure seamless integration into our existing and new software architectures.

Key Responsibilities

• Design, develop, and deploy AI and LLM-powered features for our new projects.
• Build, optimize, and maintain Retrieval-Augmented Generation (RAG) pipelines to connect LLMs with internal and external data sources.
• Integrate AI models efficiently into front-end (UI) and back-end systems.
• Collaborate with cross-functional teams to define project requirements and deliver scalable solutions.
• Optimize model performance, prompt engineering, and data pipeline integrations.
• Implement and manage data chunking, embedding generation, and indexing strategies for semantic search.
• Stay up-to-date with the latest advancements in AI, LLMs, and software engineering practices.

Required Qualifications

• Experience: Minimum 1–2 years of hands-on experience in AI and LLM development (e.g., LangChain, Langgraph or similar frameworks).
• Education: Bachelor’s or Master’s degree in Artificial Intelligence Engineering, Computer Engineering, or a related technical field.
• Strong proficiency in programming languages commonly used in AI (such as Python).
• Hands-on experience with Vector Databases (e.g., Pinecone, Qdrant, Milvus, Chroma, or pgvector) and understanding of vector embeddings.
• Practical knowledge of designing and evaluating RAG systems, including semantic search and hybrid search techniques.
• Good communication skills and a team-oriented mindset.

Preferred Qualifications (Plus)

• Strong experience or familiarity with Backend development (Python/Java etc).
• Experience or familiarity with UI / Front-end development (e.g., React etc) to facilitate smooth full-stack integration.
• Understanding of MLOps practices.

What We Offer

• Opportunity to work on cutting-edge AI and LLM technologies.
• A dynamic, collaborative, and innovation-driven work environment.