SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Preply is a unicorn edtech platform (Series D, $150M) that connects 100,000+ tutors teaching 90+ languages to learners in 180 countries. The Agentic Platform team, part of Platform Engineering, builds shared infrastructure for creating and operating reliable AI agents at scale.
As a Senior ML Platform Engineer on the Agentic Platform team, you will build production infrastructure that transforms agent prototypes into reliable, scalable systems. This is a hands-on senior role with broad technical influence—you'll write production code, shape platform abstractions, and partner across Applied Science, Data, Product, Security, and Engineering teams.
Key responsibilities:
- Design and build a durable agent runtime with checkpoints, retries, timeouts, resumability, and deterministic recovery mechanisms.
- Create a secure tool layer for discovery, registration, invocation, and versioning across internal APIs and external services (including MCP).
- 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 enabling teams to 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.
Requirements:
- 5+ years of proven track record 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/function calling, structured outputs, and multi-step workflows.
- Hands-on expertise as a forefront user of Agentic AI; ability to influence architecture, business logic, and security decisions; experience using AI as a thought partner and setting up quality gates and safety nets.
- 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) and its services/infrastructure.
- Hands-on experience with distributed tracing, system telemetry, SLOs, and incident triage.
- Strong communication skills and C1 English level; willingness to join a paid on-call rotation.
Nice to have:
- Experience with agent frameworks or durable workflow technologies (LangGraph, OpenAI Agents SDK, Temporal).
- Experience with agent evaluation, simulation, or production feedback loops.
- Experience designing sandboxed execution environments and delegated authorization for autonomous systems.
- Hands-on experience with MCP Gateway.
- Familiarity with GenAI observability and model gateways.
