We are looking for a Senior AI Engineer who combines strong software engineering fundamentals with hands-on experience shipping LLM-powered products to production. You will design and build AI features for the Kayzen Console and beyond, working across backend services, product-facing functionality, and the LLM layer
This is a hands-on engineering role. We are not looking for a research-focused ML profile or someone who has only experimented with LLMs. This role is ideal for engineers who have already built, shipped, monitored and improved production LLM systems and is comfortable contributing in a full-stack product environment
Architect, develop, and deploy production-grade LLM capabilities within the Kayzen Console
Build backend services, APIs, and integrations that connect AI capabilities with our product
Contribute to product-facing and full-stack functionality where needed
Implement production patterns for LLMs, RAG, embeddings, agents, and tool calling
Build reusable components and abstractions where they improve engineering velocity and consistency
Set up and improve evaluation, observability, monitoring, and feedback loops for AI features
Monitor and optimize quality, latency, reliability, and inference cost
Troubleshoot production issues and iterate based on telemetry and user feedback
Work closely with Product, ML and Engineering to translate product problems into pragmatic AI solutions
Prototype quickly, validate ideas, and turn successful experiments into maintainable production systems
Heavy model training or research
Designing custom ML algorithms
Academic optimization work
Building proofs of concept that never reach production