Senior Machine Learning Engineer I - ML Production (AI)

Location: Amsterdam, Netherlands; hybrid working with flexible arrangements and up to 20 days per year working from abroad in the home country. This role does not come with relocation assistance.

Company

hirify.global is a travel technology company building products and platforms that help people experience the world.

What you will do

• Architect, build, and operate scalable, low-latency distributed ML inference services for online, asynchronous, and batch predictions.
• Manage production model deployments, versioning, feature access, shadow and canary testing, and rollbacks.
• Optimize CPU, GPU, and memory utilization, lead capacity planning, and improve operational cost efficiency.
• Operate multi-cloud and on-premise Kubernetes workloads with automated scaling, CI/CD, and infrastructure as code.
• Implement telemetry, metrics, logs, traces, alerts, and SLIs/SLOs; participate in on-call response and incident follow-up.
• Partner with ML Scientists and Engineers, improve developer experience, lead technically significant initiatives, and mentor junior engineers.

Requirements

• 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.
• Experience designing distributed systems, including microservices, RPC, queues, streaming, caching, and batch systems.
• Strong understanding of concurrency, resource management, and server-side profiling.
• Hands-on experience managing production containerized Kubernetes workloads.
• Experience with cloud or hybrid infrastructure, core platform capabilities, infrastructure as code, and CI/CD.
• Experience with observability using SLIs, SLOs, metrics, logs, dashboards, and alerts.
• Understanding of ML serving, including real-time and batch inference, versioning, feature retrieval, and monitoring.
• Familiarity with on-call work, incident response, postmortems, and runbooks, plus a pragmatic customer-focused mindset and strong cross-team collaboration and English communication skills.

Nice to have

• Experience with ML serving platforms, runtimes such as Triton, ONNX Runtime, TF Serving, or TorchServe, and gateways.
• Background in JVM tuning, low-latency systems, GPU scheduling, or SRE and platform engineering.
• Familiarity with multi-cloud or hybrid scale, Spark, Kafka, Flink, Terraform, drift monitoring, or GenAI/LLMs.

Culture & Benefits

• Annual paid time off and paid parent, grandparent, bereavement, and care leave.
• Hybrid working with flexible arrangements and up to 20 days per year working from abroad in the home country.
• Product discounts of up to 1400 per year, including automatic Genius Level 3 status and hirify.global wallet credit.
• Inclusive workplace with adjustments and tools available for candidates and employees with disabilities.
• Employment is subject to applicable pre-employment screening if the application is successful.

Hiring process

• Applications follow hirify.global’s standard hiring process.
• Successful applicants may undergo third-party pre-employment screening as permitted by applicable law.