22 hours ago
Barcelona, SpainSenior
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 lifecycle, privacy, retention, and retrieval semantics.
- Design identity, scoped permissions, authorization, approvals, escalation, and handoffs for agent systems.
- Develop guardrails for tool access, policy enforcement, argument validation, sandboxing, and action limits.
- Provide 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 for agent development.
- Evaluate frameworks, workflow engines, and tool protocols while operating the platform with SLOs, capacity and cost controls, incident response, and operational standards.
- Partner with Applied Science, Data, Product, Security, and Engineering teams to shape platform architecture and technical direction.
- Participate in a paid on-call rotation.
Requirements
- At least 5 years of experience 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.
- Hands-on 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 and its services and infrastructure, preferably AWS.
- Hands-on experience with distributed tracing, system telemetry, SLOs, and incident triage.
- Strong communication skills and at least C1 English proficiency.
- Experience using AI thoughtfully in engineering workflows, including setting quality gates and safety nets and influencing architecture, business logic, and security decisions.
- Preferred experience with LangGraph, OpenAI Agents SDK, or Temporal.
- Preferred experience with agent evaluation, simulation, or production feedback loops.
- Preferred experience designing sandboxed execution environments and delegated authorization for autonomous systems.
- Preferred hands-on experience with MCP Gateway.
- Familiarity with GenAI observability, model gateways, and the boundary between shared GenAI platforms and agent runtimes.
Benefits
- Open, collaborative, dynamic, and diverse company culture.
- Monthly allowance for Preply lessons, a Learning & Development budget, and time off for self-development.
- Competitive financial package with equity, leave allowance, and health insurance.
- Attractive relocation package for joining the Preply Barcelona Hub when relocating from outside Barcelona.
- Access to free mental health support platforms.
- Access to Gympass-partnered wellness and gym centers throughout Spain.
- Opportunity to support learners and tutors in 175 countries and counting.
Categories
About Preply
Preply builds an online marketplace that connects learners with human tutors for live language lessons, supported by AI tools. Consumers book 1:1 sessions and ongoing courses, while organizations use Preply Business for corporate language training; revenue comes from commissions and subscriptions. Founded in 2012 and privately held, Preply operates globally with 100,000+ tutors teaching 90+ languages.