Own and ship AI features such as our agents, assistants, insights and more
from concept to production.
Design and implement backend services for AI integrations and data pipeline.
Build robust APIs and abstractions for internal AI usage
Drive system scalability: caching, optimization, processing patterns, etc
Contribute and drive the evolution of the infrastructure for AI including architecture, evaluation and iteration pipelines.
Solve complex AI challenges around AI accuracy, reliability, and quality – using rigorous quantitive approaches.
Advocate for our work externally – writing, speaking, and engaging with the broader AI community.
Requirements
Are an experienced backend engineer who’s shipped AI products in the OpenAI & Anthropic era – especially text and data-heavy AI applications.
Have hands-on experience with LLM orchestration and LLM API optimization (costs, latency, etc)
Are familiar with RAG architectures and technologies
Have AI observability experience. AI isn’t just about shipping features that sound great – it’s about knowing, conclusively, if they’re making things better.
Have a clear perspective on what makes a great AI product. We want to apply AI with precision, nuance, and real impact – not as a gimmick.
Are product minded and customer focused in how you build software.
Measure your success by user impact, not just technical elegance.
Are self-driven, impact-focused, and thrive in a fast-moving, high-ownership environment.
Bonus: you have experience with agent frameworks and design.