Senior ML Platform Engineer (GenAI Platform)

About the role

Preply is hiring a Senior ML Platform Engineer for its GenAI Platform team, which sits within Platform Engineering. The team builds the shared infrastructure that lets product teams develop, evaluate, deploy and operate GenAI safely at scale, working closely with ML Platform and Agentic Platform. The role is hands-on and senior, with broad technical influence.

Key responsibilities

• Design and build the systems behind production GenAI workloads, expanding the GenAI Platform into reliable self-service capabilities.
• Architect a unified gateway with automated routing, quota controls and resilient fallbacks across model vendors.
• Improve efficiency and latency through dynamic traffic management, response caching, token budgeting and cost allocation.
• Set up evaluation mechanisms for precision, stability and safety of model outputs.
• Deliver observability: tracing, performance telemetry, cost analytics, monitoring and alerting across GenAI lifecycles.
• Standardize prompt engineering workflows with automated versioning, testing, governance and CI/CD integrations.
• Work with Security and Privacy experts to embed guardrails and safe production defaults.
• Maintain incident response, blameless postmortems and monitoring for GenAI stacks.

Required profile

• 5+ years 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 with GenAI systems, including vector retrieval, external provider APIs and common issues.
• Sound knowledge of distributed systems (high availability, concurrency, caching, rate limiting).
• Experience with distributed tracing, telemetry, SLOs and incident triage.
• C1 English and willingness to join a paid on-call rotation.

Required skills

• Python
• At least one major public cloud (AWS preferred)
• Nice to have: AI gateway or model serving experience, evaluation suites, prompt management, vector databases, Metaflow, Databricks, AWS SageMaker, GPU compute optimization, agentic workflows.

What we offer

• A competitive package with equity, leave allowance and health insurance.
• Monthly allowance for lessons on Preply, a learning and development budget and time off for self-development.
• Relocation package for candidates not based in Barcelona.
• Free mental health support and access to Gympass wellness and gym centers in Spain.