Software Engineer, Full Stack (Agentic AI)

Sift is a data infrastructure platform for hardware engineering teams, founded by former SpaceX engineers. They are seeking a Full Stack Software Engineer to develop AI agents that assist hardware engineers by automating the review of telemetry data and enhancing decision-making processes.ResponsibilitiesTalk directly to customers and partner with product to turn real review workflows into agent capabilities: generating dashboards, writing analysis scripts, and surfacing insights buried in their telemetryDesign, ship, and operate agentic systems that reason over large-scale time-series data and hardware domain contextBuild everything around the model that makes agents dependable: tool interfaces, sandboxed execution for agent-generated code, context and memory management, custom compaction algorithms, opinionated skills, and guardrailsDevelop and maintain Sift’s MCP server, the tool surface that lets both our agents and our customers’ AI tools query telemetry directlyWork across the whole stackBuild the frontend surfaces where Sift Agents live, and make them feel greatDesign and implement the APIs that power our agentic capabilitiesRun agents reliably at scale, both in the cloud and on-premBuild evaluation suites that measure whether agents actually help engineers, and instrument quality, latency, cost, and failure modes in productionIntegrate and assess frontier models across providers