LLM Engineer

About the Role We are looking for a highly skilled LLM Engineer to design, develop, and optimize Large Language Model (LLM)-powered applications. This role requires deep expertise in LLM APIs, AI tool integrations, and vector database technologies. You will work with cutting-edge frameworks such as Lang Graph and DSPy, build tool-using AI systems, and leverage modern orchestration techniques to deliver intelligent, scalable, and high-performance solutions. Key Responsibilities • Design and develop LLM-powered applications integrating APIs such as Open AI, Claude, Gemini, etc. • Build AI workflows using Lang Graph, DSPy, and tool-use frameworks. • Implement MCP server integrations to extend LLM capabilities. • Work with vector databases such as Qdrant, Milvus, or Pgvector for semantic search and retrieval. • Optimize prompt engineering, model orchestration, and tool chaining for performance and accuracy. • Collaborate with cross-functional teams to translate requirements into AI-enabled solutions. • Ensure solutions adhere to best practices in security, scalability, and maintainability. • Use Azure DevOps for code management, CI/CD pipelines, and deployment. • Participate in Agile ceremonies, sprint planning, and delivery reviews. Required Skills & Qualifications • Bachelor’s or Master’s degree in Computer Science, AI/ML, Engineering, or related field. • 4+ years of experience in software development, with 2+ years in LLM/AI application development. • Strong hands-on experience with LLM APIs (Open AI, Claude, Gemini, etc.). • Experience with Lang Graph, DSPy, and tool-use patterns in AI systems. • Knowledge of MCP server integration and usage. • Expertise in vector databases (Qdrant, Milvus, Pgvector). • Familiarity with Azure DevOps and Agile delivery methodologies. • Good to Have • Experience with RAG (Retrieval-Augmented Generation) pipelines. • Knowledge of MLOps practices and AI model deployment. • Familiarity with multi-cloud environments (Azure, AWS, GCP). • Exposure to containerization (Docker, Kubernetes). Why Join Us? • Work on cutting-edge AI and LLM engineering projects. • Collaborate with top-tier AI engineers in a hybrid, innovation-driven environment. • Build solutions that leverage the latest in tool-use AI, vector search, and orchestration frameworks. Location: New York, Princeton , Chicago (Hybrid: 3 days/ week in office)