Design, build, and operate backend services for generative AI capabilities, including LLM-backed APIs, agents, retrieval and knowledge layers, and connectors to internal and external systems.
Build and scale data infrastructure underpinning file management and high-throughput data flows between customer environments, cloud object storage, and compute clusters, with an emphasis on reliability, performance, and cost.
Work across the stack—from backend services (Python/Java/Go) and cloud infrastructure (AWS/Azure/GCP, containers/Kubernetes) to the occasional UI change—to deliver end-to-end user-facing experiences in collaboration with product, design, and other engineering teams.
Requirements
1-3 years of backend software engineering experience building and operating distributed systems in a major cloud environment (AWS, Azure, or GCP).
Strong experience in at least two of Python, Java, or Go, and comfort working across service boundaries and APIs.
Experience with data-intensive systems (for example: object storage, relational databases, caches, queues/streams) and experience or strong interest in building products on top of LLMs or agents.
Experience using AI agents as part of the software development lifecycle (Claude Code or similar).
Willingness to work across the stack as needed—from backend services and cloud infrastructure to occasional frontend changes.
Strong product mindset, ability to navigate ambiguity, and effective collaboration with designers, product managers, and other engineers.