Senior Agentic AI Platform Engineer

Preply; United Kingdom; A distancia; GBP 120.000 - 160.000; Jornada completa

Descripción de la vacante

Preply is seeking a Senior ML Platform Engineer to help scale our Agentic Platform. You’ll build durable runtimes, robust tool layers, and secure state management for stateful AI agents, collaborating with multiple teams across the company.

You’ll implement distributed systems solutions, leverage Python to create developer-facing APIs, and ensure observability with telemetry and SLO-driven operations. This role offers ownership and high-impact influence within Platform Engineering.

Formación

• 5+ years designing, building, and operating backend services or ML infrastructure.
• Strong Python skills and API/SDK experience.
• Experience building GenAI-powered or agentic systems.
• Cloud experience with major providers (AWS preferred).
• Hands-on distributed tracing, telemetry, and SLOs.
• Proficient English (C1) and willingness to join paid on-call rotation.

Responsabilidades

• Build a durable agent runtime with checkpoints, retries and deterministic recovery.
• Create a secure tool layer for discovery, registration, invocation and versioning across internal APIs and external services.
• Own agent state, context and memory primitives with lifecycle and privacy semantics.
• Design identity, permissions and human controls for authorization and handoffs.
• Develop guardrails for tool access, validation, sandboxing and action limits.
• Provide end-to-end observability, trace replay and evaluation across plans and tool calls.
• Ship SDKs, templates, and tools to enable teams to build agents.
• Evaluate frameworks and workflows with clear SLOs, cost controls and incident response.

Conocimientos

Python

APIs/SDKs

GenAI/Agentic systems

Cloud (AWS)

Distributed tracing

English (C1)

On-call rotation

Herramientas

LangGraph

OpenAI Agents SDK

Temporal

Descripción del empleo

Preply is seeking a Senior ML Platform Engineer to help scale our Agentic Platform. You’ll build durable runtimes, robust tool layers, and secure state management for stateful AI agents, collaborating with multiple teams across the company.

You’ll implement distributed systems solutions, leverage Python to create developer-facing APIs, and ensure observability with telemetry and SLO-driven operations. This role offers ownership and high-impact influence within Platform Engineering.