LLM Engineer

Job Overview Pranatree LLC is looking for a skilled LLM Engineer specializing in Generative AI to join our team. This role is suitable for candidates with relevant GenAI development experience and a strong foundation in backend engineering. The position is remote and involves working on diverse projects, including both client-facing and internal initiatives focused on developing GenAI use cases such as AI assistants or content generation tools. Key Responsibilities • RAG Pipeline Development: Design and develop Retrieval-Augmented Generation (RAG) pipelines for efficient and context-aware information retrieval. • Prompt Tuning and Strategy: Implement prompt engineering and fine-tuning techniques to enhance the quality and relevance of AI outputs. • API Development: Create, maintain, and optimize backend APIs using FastAPI or similar frameworks to support AI-driven applications. • Model Deployment: Deploy and manage large language models (LLMs) such as those from OpenAI or equivalent providers, ensuring production readiness. • Cloud Integration: Utilize cloud services (AWS or Azure) for model deployment, scaling, and performance optimization. • Validation and Testing: Validate and test GenAI outputs to ensure high-quality performance and reliability. • Vector Databases and Caching: Work with vector databases and caching layers to improve data retrieval and reduce latency. • Collaboration: Partner with data scientists, engineers, and stakeholders to deliver robust solutions for both internal and client-facing projects. • Performance Monitoring: Profile, debug, and optimize large-scale machine learning systems for scalability and system performance. Qualifications and Requirements • Experience: • 12+ months of relevant GenAI development experience. • Overall 2+ years of experience in machine learning engineering. • Technical Skills: • Programming: Strong proficiency in Python. • Frameworks: Experience with FastAPI for backend API development. • LLM Expertise: Hands-on experience with large language models, including OpenAI or equivalent. • Cloud Platforms: Proficiency in cloud platforms such as AWS or Azure. • Production Deployment: Experience in deploying LLM-based products into production environments. • Project Experience: • Involvement in projects that include GenAI use cases like developing AI assistants or content generation tools. • Familiarity with prompt tuning, RAG pipeline creation, and validation of generative outputs. • Working with vector databases and caching for optimizing data retrieval. • Other Skills: • Strong understanding of machine learning system performance, including profiling, debugging, and scalability. • Good communication skills for collaborative work and client interactions when needed. Performance Expectations • Design and deploy efficient RAG pipelines and GenAI solutions that align with project requirements. • Optimize backend systems and APIs for seamless integration with GenAI models. • Ensure scalable, reliable, and high-performance solutions. • Collaborate effectively with cross-functional teams and stakeholders. • Participate in client interviews for external projects if required.