AI Engineer (Full-Time or Contract)
On-siteTirana, Tirana, Albania
Job Summary
Deploy and optimize open-source Large Language Models (LLMs) while designing, implementing, and maintaining private on-premise AI systems. Develop Retrieval-Augmented Generation (RAG) architectures and build AI-powered pipelines for processing PDFs and other document formats. Configure GPU-based inference environments and local AI infrastructure to automate the analysis of legal and business documents. Construct AI systems capable of generating response letters based on historical data and similar cases. This role involves hands-on work with Python, OCR technologies, and document understanding within Oracle Law Global's Tirana office, focusing on real-world AI projects involving large language models and document intelligence.
Required Qualifications
- Hands-on experience with AI and Large Language Model (LLM) technologies
- Strong proficiency in Python
- Practical experience with RAG, embeddings, and vector databases
- Experience in document classification and document understanding
- Knowledge of OCR technologies and document processing pipelines
- Strong prompt engineering skills and experience with AI agents
- Experience deploying and managing on-premise AI environments
- Experience with GPU inference, model deployment, and performance optimization
Desired Qualifications
- Experience with technologies such as vLLM, Ollama, Hugging Face Transformers, LangChain, LlamaIndex, or similar Ollama frameworks
- Experience working with NVIDIA GPUs and the CUDA ecosystem
- Experience in LegalTech or document automation projects
- Familiarity with Docker, Linux, and Microsoft Azure environments
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.