Senior AI Platform Engineer - Agentic Runtime & Tools

Preply; España; Vor Ort; EUR 90.000 - 120.000; Vollzeit

Zusammenfassung

Preply is advancing its AI-driven learning platform with the Agentic Platform team. We build shared infrastructure and abstractions to empower product and engineering teams to create and operate reliable AI agents.

This senior role shapes runtime, tooling, and platform evolution, partnering across engineering, data, security, and product teams. You will own production-grade ML infrastructure, implement durable runtimes, and drive architectural decisions while contributing hands-on code and

Qualifikationen

• 5+ years designing, building, and operating backend services or ML infrastructure handling production traffic.
• Strong Python skills and experience building developer-facing APIs/SDKs or shared libraries.
• Experience building GenAI-powered or agentic systems using tool or function calling, structured outputs, and multi-step workflows.
• AI Expertise: hands-on experience with Agentic AI, influencing architecture, business logic and security decisions.
• Experience integrating production services through APIs and events, including authentication, authorization, and secure service-to-service interaction.
• Experience with at least one major public cloud, preferably AWS.
• Hands-on experience with distributed tracing, system telemetry, SLOs, and incident triage.
• Strong communication skills and at least C1 English level, plus willingness to join a paid on-call rotation.

Aufgaben

• Build a durable agent runtime with checkpoints, retries, timeouts, resumability, and deterministic recovery where possible.
• Create a secure tool layer for discovery, registration, invocation and versioning across internal APIs and external services, including MCP where useful.
• Own agent state, context and memory primitives with clear lifecycle, privacy, retention and retrieval semantics.
• Design identity, scoped permissions and human controls for authorization, approvals, escalation and handoffs.
• Develop guardrails for tool access, policy enforcement, argument validation, sandboxing and action limits.
• Provide end‑to‑end observability, trace replay and scenario‑based evaluation across plans, model calls, tool calls, state transitions and outcomes.
• Ship SDKs, templates, local tools, documentation and paved‑road patterns so teams can build agents without re‑solving runtime infrastructure.
• Evaluate frameworks, workflow engines, and tool protocols while operating the platform with clear SLOs, capacity and cost controls, incident response, and operational standards.

Kenntnisse

Python

Backend services

APIs/SDKs

GenAI

AWS

Distributed tracing

English (C1)

On-call rotation

Tools

LangGraph

OpenAI Agents SDK

Temporal

Jobbeschreibung

Preply is advancing its AI-driven learning platform with the Agentic Platform team. We build shared infrastructure and abstractions to empower product and engineering teams to create and operate reliable AI agents.

This senior role shapes runtime, tooling, and platform evolution, partnering across engineering, data, security, and product teams. You will own production-grade ML infrastructure, implement durable runtimes, and drive architectural decisions while contributing hands-on code and