Backend / AI Infrastructure Engineer

Role overview Build and operate the backend infrastructure that helps AI systems run reliably and safely in production. The work spans model serving, orchestration, durable execution, observability, security, and cost management, with responsibility for delivering systems into real production environments.

Responsibilities - Design and build infrastructure for AI serving, orchestration, retries, and durable execution. - Make system runs traceable and debuggable using observability tools, metrics, and replay capabilities. - Strengthen security and access controls for enterprise use. - Monitor and manage the costs of LLM workloads. - Work with a small team to take systems through implementation and production delivery.

Requirements - Strong backend engineering skills in Python, Go, or both. - Experience operating production services. - Practical understanding of reliability, retry behavior, tracing, and cost control in AI or LLM systems. - Ability to own a system end to end in a small team. - Clear written communication in code reviews and design documents.

Nice to have - Experience with event sourcing or durable execution tools such as Temporal. - Background in large-scale MLOps, LLM gateways, or agent frameworks. - Relevant open-source contributions.

Benefits and work setup - Fully remote, with work arranged within your timezone. - Ownership of your area from the start, with direct access to founders. - Small, experienced team and an async-first culture with few meetings.