Senior ML Platform Engineer (Agentic Platform)

The role

You will build the infrastructure that takes agent prototypes to production. You will solve distributed-systems problems in long-running, non-deterministic workflows and write production code to shape platform abstractions.

What you will do

• Build a durable agent runtime with checkpoints, retries, timeouts, resumability, and deterministic recovery
• Create a secure tool layer for discovery, registration, invocation and versioning
• Own agent state, context and memory primitives
• 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
• Ship SDKs, templates, local tools, documentation and paved-road patterns
• Evaluate frameworks, workflow engines, and tool protocols
• Operate the platform with clear SLOs, capacity and cost controls, incident response, and operational standards

Required qualifications

• 5+ years designing, building, and operating backend services or ML infrastructure handling production traffic
• Strong Python skills
• 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
• AI Expertise in Agentic AI
• 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, its services and infrastructure
• Hands-on experience with distributed tracing, system telemetry, SLOs, and incident triage
• Strong communication skills
• C1 English level

Nice to have

• Experience with agent frameworks or durable workflow technologies such as LangGraph, OpenAI Agents SDK, or Temporal
• Experience with agent evaluation, simulation, or production feedback loops
• Experience designing sandboxed execution environments, delegated authorization for autonomous systems
• Hands-on experience with MCP Gateway
• Familiarity with GenAI observability and model gateways

Benefits

• Monthly allowance for lessons on Preply
• Learning & Development budget
• Time off for self-development
• Competitive financial package with equity
• Leave allowance
• Health insurance
• Access to free mental health support platforms
• Access to Gympass-partnered wellness and gym centers throughout London

About the company

Preply is a category-defining company that helps people discover tutors and craft personalised learning journeys. They have reached unicorn status with a $150M Series D.