Senior ML Platform Engineer (Agentic Platform)

About the role

Preply is hiring a Senior ML Platform Engineer for its Agentic Platform team, which sits within Platform Engineering and builds shared infrastructure and abstractions for reliable AI agents. The team works closely with GenAI Platform and ML Platform, composing them into a runtime and developer experience for stateful, action-taking AI systems. This is a hands-on senior role with broad technical influence, writing production code and partnering with Applied Science, Data, Product, Security and Engineering teams.

Key responsibilities

• 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.

Required profile

• 5+ years designing, building and operating backend services or ML infrastructure handling production traffic.
• Experience building GenAI-powered or agentic systems using tool or function calling, structured outputs and multi-step workflows.
• Experience integrating production services through APIs and events, including authentication, authorization and secure service-to-service interaction.
• Strong communication skills and at least C1 English, plus willingness to join a paid on-call rotation.

Required skills

• Strong Python and experience building developer-facing APIs, SDKs or shared libraries.
• Experience with at least one major public cloud and its services (preferably AWS).
• Hands-on experience with distributed tracing, system telemetry, SLOs and incident triage.
• Nice to have: agent frameworks or durable workflow technologies such as LangGraph, OpenAI Agents SDK or Temporal; agent evaluation and sandboxed execution design; MCP Gateway; GenAI observability and model gateways.

What we offer

• A generous monthly allowance for lessons on Preply.com, a Learning & Development budget and time off for self-development.
• A competitive financial package with equity, leave allowance and health insurance.
• Relocation package for candidates not based in Barcelona.
• Free mental health support platforms and access to Gympass-partnered wellness and gym centers in Spain.