We are looking for a highly motivated AI Engineer to join our core team. From day one, your work will help shape the intelligence of our product, working directly on advanced AI infrastructure with experienced engineers.
KEY RESPONSIBILITIES
Design and build core AI systems that combine LLMs, retrieval, and memory to power conversational intelligence
Prototype rapidly with new models and techniques, evaluate their performance, and productionize the best approaches
Engineer scalable and reliable backend components in Python (FastAPI, asyncio) to support real-time user interactions
Architect Retrieval Augmented Generation (RAG) pipelines with vector and graph databases to enable long-term context and personalization
Work closely with product and frontend teams to integrate AI features seamlessly into the user experience
Stay current with AI research and apply new ideas to continually improve our systems
WHAT WE EXPECT
Strong Python skills with the ability to ship clean, reliable, and scalable production code
Experience designing real-time backend systems (FastAPI, asyncio) for high-performance applications
Hands-on expertise with LLMs, from integrating APIs (OpenAI, Gemini, etc.) to evaluating and optimizing outputs for real use cases
Ability to design effective prompts and build Retrieval Augmented Generation (RAG) pipelines using vector and graph databases
Familiarity with intelligent agent design and multi-agent orchestration
Solid foundation in data structures, algorithms, and system design, with the pragmatism to apply them in production
Clear communication skills, attention to detail, and a strong sense of ownership in a fast-moving startup environment
WHY JOIN US
Impact: Your work directly shapes our AI’s intelligence
Learning: Exposure to advanced AI stacks and multi-agent systems
Culture: High standards, precision, and engineering excellence
Growth: Accelerate your career with equity and rapid responsibilities