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 company is integrating GenAI into its core product strategy to enhance personalized learning experiences.
The GenAI Platform team sits within Platform Engineering and builds shared infrastructure enabling product teams to develop, evaluate, deploy, and operate GenAI safely at scale. The team owns the GenAI gateway, model and prompt lifecycle management, evaluation frameworks, observability, cost controls, and guardrails. You will work closely with ML Platform (core ML workflows) and Agentic Platform (agent orchestration, state management, tool integration) teams.
As a Senior ML Platform Engineer, you will design and build production GenAI systems with hands-on technical influence. This is a broad-scoped role where you write production code, shape platform abstractions, and establish operational standards. You will partner with Applied Science, Data, Product, Security, and Engineering teams across the organization.
Key responsibilities:
- Architect a unified GenAI gateway with automated routing, quota controls, and resilient fallback systems across multiple model vendors.
- Drive system efficiency and low latency through dynamic traffic management, response caching, token budgeting, and cost allocation controls.
- Establish robust evaluation mechanisms to ensure high precision, stability, and safety in model outputs.
- Deliver comprehensive system observability including deep tracing, performance telemetry, cost analytics, continuous monitoring, and alerting across GenAI lifecycles.
- Standardize prompt engineering workflows with automated versioning, testing, governance, and CI/CD integrations for production delivery.
- Embed platform guardrails alongside Security and Privacy teams to enforce policies and safe production defaults automatically.
- Maintain sustainable incident response, blameless postmortems, and comprehensive monitoring for GenAI stacks.
You will work in small teams with significant ownership, directly shaping system architecture and platform evolution. The role involves hands-on coding, architectural decisions, and operational leadership.
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.
- Practical experience with GenAI systems, including vector retrieval, external provider APIs, and common production issues.
- AI Expertise: Hands-on experience as a forefront user of Agentic AI; ability to influence architecture, business logic, and security decisions; experience using AI as a thought partner and establishing quality gates and safety nets; capability to propose AI-native engineering alternatives.
- Sound knowledge of distributed systems, including high availability, concurrency, caching, and rate limiting.
- Experience with at least one major public cloud and its services/infrastructure (preferably AWS).
- Hands-on experience with distributed tracing, system telemetry, SLOs, and incident triage.
- Strong communication skills and C1 English level proficiency.
- Willingness to join a paid on-call rotation.
NICE TO HAVE:
- Experience operating AI gateways or scalable model serving infrastructure.
- Familiarity with evaluation suites, prompt management, vector databases, or customized GenAI observability tooling.
- Experience with Metaflow, Databricks, or AWS SageMaker.
- Knowledge of hosting open-source foundation models, optimizing GPU compute, dynamic scaling, and infrastructure cost controls.
- Familiarity with agentic workflows, multi-agent frameworks, and tool-use patterns.
