29 days ago
Kyiv, UkraineSenior
Responsibilities
- Build a durable agent runtime with checkpoints, retries, timeouts, resumability, and recovery capabilities.
- Create secure tooling for discovery, registration, invocation, and versioning across internal APIs and external services, including MCP where useful.
- Own agent state, context, and memory primitives with defined privacy, retention, lifecycle, and retrieval semantics.
- Design identity, scoped permissions, approvals, escalations, handoffs, guardrails, sandboxing, and action limits.
- Develop observability, trace replay, and scenario-based evaluation across model calls, tool calls, state transitions, and outcomes.
- Ship SDKs, templates, local tools, documentation, and paved-road patterns for agent developers.
- Evaluate frameworks and workflow engines 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 with production API and event integrations, authentication, authorization, and secure service-to-service interactions.
- 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.
- Willingness to participate in a paid on-call rotation.
- Preferred experience with LangGraph, OpenAI Agents SDK, Temporal, agent evaluation, simulation, production feedback loops, sandboxed execution, delegated authorization, MCP Gateway, GenAI observability, or model gateways.
Benefits
- Generous monthly allowance for lessons on Preply.com.
- Learning and Development budget, including time off for self-development.
- Competitive financial package with equity and leave allowance.
- Opportunity to shape learning experiences for learners and tutors across more than 175 countries.
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.