ОписаниеPreply creates learning experiences that help people find tutors, build personalized learning journeys, and stay motivated. Its platform connects over 100,000 tutors teaching more than 90 languages to learners in 180 countries.ЗадачиBuild a durable agent runtime with checkpoints, retries, timeouts, resumability, and deterministic recovery where possibleCreate a secure tool layer for discovery, registration, invocation, and versioning across internal APIs and external services, including MCP where usefulOwn agent state, context, and memory primitives with clear lifecycle, privacy, retention, and retrieval semanticsDesign identity, scoped permissions, and human controls for authorization, approvals, escalation, and handoffsDevelop guardrails for tool access, policy enforcement, argument validation, sandboxing, and action limitsProvide end-to-end observability, trace replay, and scenario-based evaluation across plans, model calls, tool calls, state transitions, and outcomesShip SDKs, templates, local tools, documentation, and paved-road patterns so teams can build agents without re-solving runtime infrastructureEvaluate frameworks, workflow engines, and tool protocolsOperate the platform with clear SLOs, capacity and cost controls, incident response, and operational standardsТребования5+ Years designing, building, and operating backend services or ML infrastructure handling production trafficStrong Python skillsExperience building developer-facing APIs/SDKs or shared librariesExperience building GenAI-powered or agentic systems using tool or function calling,



structured outputs, and multi-step workflowsHands-on experience with Agentic AI, influencing the team beyond code generation, applying judgment to architecture, business logic, and security, using AI as a thought partner, and setting up quality gates and safety nets to enhance engineering workflows and propose AI-native alternativesExperience integrating production services through APIs and events, including authentication, authorization, and secure service-to-service interactionExperience with at least one major public cloud and its services and infrastructure; AWS is preferredHands-on experience with distributed tracing, system telemetry, SLOs, and incident triageStrong communication skillsEnglish at C1 level or higherWillingness to join a paid on-call rotationБудет плюсом: experience with agent frameworks or durable workflow technologies such as LangGraph, OpenAI Agents SDK, or Temporal; agent evaluation, simulation, or production feedback loops; sandboxed execution environments; delegated authorizationfor autonomous systems; MCP Gateway; GenAIobservability and model gateways, including the boundary between a shared GenAI platform and the Agent RuntimeУсловияA generous monthly allowance for lessons, a Learning & Development budget, and time off for self-developmentA competitive financial package with equity, leave allowance, and health insuranceRelocation package to join the Barcelona HubFree mental health support platformsAccess to Gympass-partnered wellness and gym centers throughout Spain#J-18808-Ljbffr

📌 Ml Platform Engineer For Agentic Platform (Madrid)
🏢 Preply
📍 Madrid