21 hours ago
London, United KingdomSenior
Responsibilities
- Build a durable agent runtime with checkpoints, retries, timeouts, resumability, and deterministic recovery where possible.
- Create a secure tool layer for discovering, registering, invoking, and versioning 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, escalations, handoffs, guardrails, 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 agent 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 and participate in a paid on-call rotation.
Requirements
- 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, at least C1 English proficiency, and willingness to join a paid on-call rotation.
- Preferred experience with LangGraph, OpenAI Agents SDK, Temporal, agent evaluation or simulation, sandboxed execution environments, delegated authorization, MCP Gateway, GenAI observability, or model gateways.
- Ability to use Agentic AI thoughtfully, apply architectural and security judgment, establish quality gates and safety nets, and propose AI-native engineering workflows.
Benefits
- Monthly allowance for language lessons, a Learning & Development budget, and time off for self-development.
- Competitive financial package with equity, leave allowance, and health insurance.
- Access to free mental health support platforms.
- Access to Gympass-partnered wellness and gym centers throughout London.
- Opportunity to support language learning and teaching in 175 countries.
- Paid on-call rotation is part of the role.
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.