Job Description
Overview
We design and build enterprise-grade Generative AI solutions that run in production. LLMs are treated as software components within robust, scalable, and observable systems, not as experimental tools. Our solutions are cloud-agnostic by design, and can be deployed on Azure, AWS, or GCP, while selectively leveraging managed services when they add real value (e.g. search, AI, or data platforms).
Responsibilities
- Your mission is to own the technical design and implementation of end-to-end Generative AI solutions, ensuring strong software engineering practices, sound architectural decisions, and reliable integration of LLM-based components into real-world systems.
- This role is hands-on and technical, with responsibility for technical leadership, mentoring, and architectural decision-making.
- Design and build scalable backend systems in Python (APIs, services, pipelines).
- Integrate LLMs into production systems (RAG, work...