Principal AI Engineer (LLM Agents & Orchestration)

About the Role

The role entails working on complex AI systems, collaborating with a team of exceptionally smart individuals, and driving the development of autonomous agents that can plan, execute, and self-correct. You will be part of a fast-moving team that values innovation, data-driven decisions, and growth.

What You Will Do

• Design and implement stateful agentic workflows using frameworks like LangGraph or custom Python/TypeScript solutions
• Develop robust integration layers for the LLM to interact with internal APIs, databases, and third-party tools
• Optimize inference pipelines for speed and reliability
• Architect advanced RAG (Retrieval-Augmented Generation) systems for persistent memory and context awareness
• Establish a rigorous testing framework for non-deterministic model outputs
• Collaborate with the engineering team to design event-driven architectures
• Work on vector search and embedding strategies
• Develop and maintain technical documentation for the 'Super Agent' system
• Participate in code reviews and contribute to the improvement of the codebase
• Stay up-to-date with the latest advancements in LLMs and AI research

What We Are Looking For

• Deep expertise in Large Language Models (LLMs) and their applications
• Strong proficiency in Python (or TypeScript) and the modern AI stack (LangChain, LlamaIndex, DSPy)
• Experience with model internals and Function Calling/Tool Use
• Hands-on experience with vector databases (Pinecone, Milvus, Weaviate) and embedding strategies
• Strong understanding of system design and event-driven architectures
• Excellent problem-solving skills and ability to work in a fast-paced environment
• Strong communication and collaboration skills
• Experience with testing and validation of non-deterministic model outputs

Nice to Have

• Experience with LangGraph or similar frameworks
• Knowledge of computer vision and image generation models
• Familiarity with cloud-based infrastructure and containerization (Docker)
• Experience with agile development methodologies and version control systems (Git)

Benefits and Perks

• Competitive compensation and benefits package
• Opportunity to work on innovative AI products and shape the future of creativity and user interaction
• Collaborative and dynamic work environment with a team of exceptionally smart individuals
• Flexible working hours and remote work options
• Professional development and growth opportunities
• Access to the latest tools and technologies in AI research and development
• Recognition and rewards for outstanding performance and contributions
• Comprehensive health and wellness programs
• Generous paid time off and holiday leave

• Develop a strong portfolio that showcases your expertise in LLMs and AI research, including any published papers, projects, or presentations.
• Familiarize yourself with ImagineArt's products and technology stack to demonstrate your understanding of the company's vision and goals.
• Prepare to discuss your experience with model internals, Function Calling/Tool Use, and vector search, as well as your approach to testing and validation of non-deterministic model outputs.
• Showcase your problem-solving skills and ability to work in a fast-paced environment by providing examples of complex projects you've worked on and how you overcame challenges.
• Be prepared to discuss your long-term career goals and how they align with ImagineArt's mission and vision.
• Research the company culture and values to ensure you're a good fit, and be prepared to ask questions about the team, the role, and the company's future plans.