We are seeking an experienced LLM Engineer to join our team and contribute to the development and deployment of AI-powered applications. This role will focus on utilizing large language models (LLMs) to solve real-world problems through fine-tuning, prompt engineering, integration with various data sources, and building agentic workflows.

Responsibilities:

• Fine-tune open-source LLMs, including smaller language models (SLMs), using domain-specific datasets to improve performance in targeted applications.
• Develop and implement prompt engineering strategies to optimize LLM responses.
• Build and maintain Retrieval-Augmented Generation (RAG) pipelines to enhance LLM knowledge and accuracy.
• Design, build, and deploy sophisticated AI Agents that leverage LLMs to automate complex tasks and workflows (Agentic workflows).
• Collaborate with MLOps engineers to deploy and monitor LLM applications in cloud environments.
• Evaluate model performance using robust evaluation metrics and implement strategies for continuous improvement.
• Implement LLM observability and monitoring solutions to ensure model health and performance in production.
• Identify areas for improvement and implement solutions based on evaluation results.

Requirements:

• Bachelor’s or Master’s degree in Computer Science, AI, Machine Learning, or a related field.
• Strong proficiency in Python and relevant libraries, including: PyTorch, Hugging Face Transformers, FastAPI.
• Hands-on experience in fine-tuning LLMs and implementing prompt engineering techniques.
• Familiarity with vector databases (e.g., Qdrant, Pinecone, Weaviate) for RAG applications.
• Experience with cloud platforms (AWS, GCP, or Azure) for model deployment.
• Good communication and collaboration skills.
• Knowledge of model quantization techniques to improve inference speed.
• Experience with generating synthetic data and supervised fine tuning.
• Knowledge of RLHF (Reinforcement Learning from Human Feedback) to improve model alignment.