AI Engineer

As an AI Engineer at our company, your role will involve designing, developing, and deploying an in-house AI assistant powered by LLaMA 3 and integrated with our MS SQL-based ERP system (4QT ERP). You will be responsible for setting up LLM infrastructure, implementing voice input (Whisper), translating natural language to SQL, and ensuring accurate, context-aware responses to ERP-related queries. Key Responsibilities: - Setup and deploy LLaMA 3 (8B/FP16) models using llama-cpp-python or Hugging Face - Integrate the AI model with FastAPI to create secure REST endpoints - Implement prompt engineering or fine-tuning (LoRA) to enhance SQL generation accuracy - Develop a user-facing interface (React or basic web UI) for text or voice interactions - Integrate Whisper (OpenAI) or any STT system to support voice commands - Ensure that model responses are secure, efficient, and auditable (only SELECT queries allowed) - Supervise or perform supervised fine-tuning with custom ERP datasets - Optimize for performance (GPU usage) and accuracy (prompt/RAG tuning) Qualifications Required: - Strong experience with LLM deployment (LLaMA 3, Mistral, GPT-type models) - Solid Python development experience using FastAPI or Flask - Proficiency in SQL, especially with MS SQL Server, and ability to write and validate queries - Experience with llama-cpp-python, Hugging Face Transformers, and LoRA fine-tuning - Familiarity with LangChain or similar LLM frameworks - Understanding of Whisper (STT) or equivalent Speech-to-Text tools - Experience working with GPU inference (NVIDIA 4070/5090 etc.) This job is suitable for freshers and the work location is in person.,