About The Role

Syndi is Syndio's AI platform — a single agent runtime serving product lines, built on syndi-api: an agent runtime owning orchestration, tool calling, memory, RAG, evals, and observability, currently live in production. The platform is young (v1 shipped this quarter) and organized around an operating model where product teams contribute domain content via APIs, evals, and knowledge, while the platform owns the experience. We are hiring a staff-level engineer to own major runtime surfaces and grow into a technical owner of the platform. This high-autonomy role on a small team (3–4 engineers) will design, ship, and operate end-to-end systems and collaborate with product-team owners through the platform's contribution seams. What you'll work on:

• Core runtime surfaces of syndi-api: the agent loop, tool execution and registry, memory, and context management (Python, Postgres, Claude on Vertex, GCP).
• The eval system: offline gates and online detector/judge evals produced from production traces, expanding as product teams adopt it.
• Production operations: observability (Datadog LLM Obs), incident response, and reliability of an agent surface used by real customers.
• The platform's contribution seams: reviewing product teams' tool wrappers and evals, evolving the GET /tools registry and drift-detection contract.
• Clarifying,

About The Role

Syndi is Syndio's AI platform — a single agent runtime serving product lines, built on syndi-api: an agent runtime owning orchestration, tool calling, memory, RAG, evals, and observability, currently live in production. The platform is young (v1 shipped this quarter) and organized around an operating model where product teams contribute domain content via APIs, evals, and knowledge, while the platform owns the experience. We are hiring a staff-level engineer to own major runtime surfaces and grow into a technical owner of the platform. This high-autonomy role on a small team (3–4 engineers) will design, ship, and operate end-to-end systems and collaborate with product-team owners through the platform's contribution seams. What you'll work on:

• Core runtime surfaces of syndi-api: the agent loop, tool execution and registry, memory, and context management (Python, Postgres, Claude on Vertex, GCP).
• The eval system: offline gates and online detector/judge evals produced from production traces, expanding as product teams adopt it.
• Production operations: observability (Datadog LLM Obs), incident response, and reliability of an agent surface used by real customers.
• The platform's contribution seams: reviewing product teams' tool wrappers and evals, evolving the GET /tools registry and drift-detection contract.
• Clarifying,

Правовое

• Конфиденциальность
• Условия
• Cookies

Правовое

• Конфиденциальность
• Условия
• Cookies