LLM Engineer – AI Core Delivery

About the role

Masterworks is seeking a highly skilled LLM Engineer to join the AI Core Delivery team within the AI & Analytics Center of Excellence. The role focuses on developing, deploying, and optimizing advanced language model capabilities, including Retrieval‑Augmented Generation pipelines and agentic AI systems. You will help scale the enterprise AI platform by ensuring production‑ready performance, observability, and seamless integration with internal and external systems.

Key responsibilities

• Build and optimize Retrieval‑Augmented Generation (RAG) pipelines for document processing, indexing, and retrieval.
• Implement agentic AI logic for tool integration, task automation, and external data access.
• Enhance query understanding, response ranking, and output quality; develop evaluation benchmarks.
• Collaborate with API developers and backend engineers to deliver secure, observable LLM endpoints.
• Deploy and manage LLMs in cloud‑native or hybrid environments, ensuring scalability and multi‑cloud readiness.
• Implement CI/CD workflows for model updates, rollback mechanisms, and performance tuning.
• Integrate LLM capabilities with enterprise data sources and knowledge bases; support multi‑source retrieval and embedding strategies.
• Apply enterprise‑grade authentication, access management, and encryption; ensure compliance with governance, privacy, and audit requirements.
• Monitor system performance, debug issues, and fine‑tune models based on real‑world feedback; stay updated on LLM advancements.

Required profile

• Bachelor’s or Master’s degree in Computer Science, AI, Data Science, or a related field.
• Hands‑on experience developing and deploying large language models (e.g., OpenAI, Anthropic, Hugging Face, LLaMA).
• Strong understanding of Retrieval‑Augmented Generation, embeddings, and vector databases.
• Experience with cloud platforms (AWS, Azure, GCP) and Infrastructure‑as‑Code.
• Proficiency in Python for AI/ML pipeline development.
• Familiarity with container orchestration (Docker, Kubernetes) and CI/CD practices.

Required skills

• LLaMA
• Hugging Face
• OpenAI
• Anthropic
• Python
• Observability tools
• Cloud platforms (AWS, Azure, GCP)
• Infrastructure‑as‑Code
• Docker
• Kubernetes
• CI/CD pipelines
• Vector databases / embeddings