About the Role
This platform automates document processing and data retrieval for enterprise customers, operating in highly sensitive financial environments where compliance isn't optional. Backed by leading investors, they've recently secured significant Series A funding, positioning them as one of the fastest-growing enterprise AI platforms globally. You'll join a lean team, reporting directly to the founders, to drive the AI-product surface.
Responsibilities
•Develop and deploy production-grade AI features, including RAG systems, multi-agent infrastructure, and robust evaluation frameworks.
•Build the backend services and APIs that power these AI applications.
•Design and implement data pipelines for training, evaluation, and continuous improvement of AI models.
•Ensure the scalability, performance, and security of AI systems across the entire stack.
•Mentor junior engineers and contribute to team growth.
Requirements
•5+ years of professional software engineering experience, with a track record of shipping production systems.
•Proven experience building and deploying AI applications in production, specifically with RAG pipelines, agent orchestration, and performance monitoring.
•Fluency in LLM evaluation techniques for accuracy, reliability, and safety.
•Strong backend development skills in Python (Django/FastAPI preferred) and relational databases.
•Experience with cloud infrastructure, Docker, Kubernetes, CI/CD, and managing high-throughput background workers and queues.
Conditions
No conditions specified in the posting.
