Senior ML Platform Engineer: Low-Latency Inference—Hybrid

Booking.com; Amsterdam; On-site; EUR 110,000 - 170,000; Full time

Benefits offered by this job

Annual leave and flexible time off

Hybrid working arrangements

Booking.com discounts and perks

Job summary

Booking.com is seeking a Senior Machine Learning Engineer I to design, build, and operate platform capabilities for reliable ML inference at scale. You’ll work on integrating models into robust services, optimize a JVM-based, multi-cloud stack, and drive platform engineering improvements across real-time and batch workloads.

You will lead technical directions, mentor peers, and collaborate with ML scientists and engineers to productionize models while balancing reliability, latency, cost, and

Qualifications

• Experience deploying and operating ML models in production across backend, infrastructure, or SRE domains.
• Proficiency in Java, Scala, JVM languages, or Python with strong backend engineering skills.
• Proven background designing distributed systems (microservices, RPC, queues, streaming, caching, batch).
• Solid grasp of concurrency, resource management, and server-side profiling.

Responsibilities

• Architect, build, and operate scalable, low-latency distributed ML inference services and prediction systems across online, async, and batch workloads.
• Manage production model deployments, model versioning, feature access, shadow/canary testing, and rollbacks.
• Operate multi-cloud and on-premise Kubernetes workloads with automated scaling, CI/CD, and IaC practices.
• Implement end-to-end telemetry (metrics, logs, traces, alerts) and maintain SLIs/SLOs, contributing to on-call response.

Skills

Java/Scala

Distributed systems

Kubernetes

Cloud & on-prem

Observability

English communication

CI/CD

Tools

Terraform

Docker

Kafka

ML Serving platforms

Job description

Booking.com is seeking a Senior Machine Learning Engineer I to design, build, and operate platform capabilities for reliable ML inference at scale. You’ll work on integrating models into robust services, optimize a JVM-based, multi-cloud stack, and drive platform engineering improvements across real-time and batch workloads.

You will lead technical directions, mentor peers, and collaborate with ML scientists and engineers to productionize models while balancing reliability, latency, cost, and