We’re seeking an entrepreneurial engineer who will work closely with the founders to build and scale the world’s first Living World RPG, and ushers in the next generation of role playing games.

This is a critical product engineering role with the additional ownership that comes with being among our initial engineering team. You’ll play a fundamental role in shaping the product and scaling the team as it grows.

RESPONSIBILITIES

• Especially in your first year, you’ll play a pivotal role in shaping our AI engineering practices:
• Work closely with our AI team to design and implement agentic RAG applications using python, while ensuring seamless integration and data exchange with backend and frontend systems.
• Collaborate with our backend team to build the engine powering games on the Infinity Fiction Platform and our first game: Tidefall
• Develop and maintain reusable, modular, and scalable applications using modern python frameworks and libraries
• Participate in code reviews and contribute to the development of technical standards and best practices
• Mentor junior engineers and provide guidance on development best practices
• Stay up-to-date with the latest AI technologies and trends, applying this knowledge to drive innovation and improvement in our platform
• Build and deploy robust AI applications using technologies such as Llamanindex and LangChain for seamless orchestration of LLM (large language model) pipelines.
• Design workflows that incorporate memory, retrieval, multi-step reasoning, and tool integrations to enhance AI agent capabilities.

REQUIRED SKILLS & EXPERIENCE

• Proven experience in AI and RAG applications development, with a strong focus on Python modern frameworks and libraries
• Proven experience in designing and developing AI systems that leverage agentic capabilities within RAG frameworks to autonomously retrieve, process, and refine information for enhanced decision-making and response generation. Optimize retrieval workflows, response accuracy, and adaptive reasoning.
• Experience in  efficient structuring, indexing, and retrieval of large-scale unstructured and structured data for AI-driven applications. Experience with  retrieval strategies using vector/graph database technologies.
• Experience in developing ingestion workflows/pipelines for vector indexes using well known providers (e.g., FAISS, Pinecone, Weaviate, Chroma)
• Experience with testing methodologies (unit/functional/e2e) and tools (unittest, pytest, etc.)
• Experience with agile development methodologies and version control systems (e.g., Git)
• Excellent problem-solving skills and the ability to adapt to a fast-paced, evolving environment.

DESIRABLE SKILLS & EXPERIENCE

• GraphRAG technologies such as Neo4j
• Database Management Systems: MongoDB, PostgreSQL, MySQL, SQL-Lite
• Knowledge of RESTful APIs and experience in API design and implementation.
• Experience in developing ingestion workflows/pipelines for vector indexes using well known providers (e.g., FAISS, Pinecone, Weaviate, Chroma)
• Build and deploy robust AI applications using technologies such as Llamanindex and LangChain for seamless orchestration of LLM (large language model) pipelines.
• Design workflows that incorporate memory, retrieval, multi-step reasoning, and tool integrations to enhance AI agent capabilities

Apply