xelys jobs xelys jobs

Machine Learning Platform Engineer

Bjak

midpermanentbackenddata Germany 99 days ago via Arbeitnow

See how well this job matches your profile

Sign up to get an AI match score and generate a tailored application in seconds.

Get your match score

Tags

Machine LearningML InfrastructureModel DeploymentInference OptimizationObservabilityDistributed SystemsData PipelinesEvaluation & BenchmarkingCI/CDVector Databases

About the role

Role Overview

As a Machine Learning Platform Engineer, you will build and operate the infrastructure that powers A1’s AI capabilities—from training and evaluation to deployment, inference, observability, and continuous improvement.

Responsibilities

  • Build and operate ML infrastructure and platforms for AI products.
  • Design systems for model training, evaluation, deployment, inference, and experimentation.
  • Build and optimize model serving and inference infrastructure for high-throughput, low-latency workloads.
  • Improve reliability, scalability, latency, and cost efficiency across AI systems.
  • Develop reliable pipelines for data preparation, training, evaluation, model release, and continuous improvement.
  • Create platforms and tooling to help AI engineers and researchers experiment, evaluate, and ship models faster.
  • Build evaluation and benchmarking infrastructure to measure quality, performance, and regressions.
  • Implement production observability: monitoring, tracing, and alerting for AI/ML workloads.
  • Identify bottlenecks across the ML stack and drive continuous performance improvements.
  • Partner with AI, research, and product teams to turn evolving model requirements into production-ready infrastructure.

Requirements

  • Strong software engineering fundamentals and experience building production systems.
  • Hands-on experience building ML infrastructure / production ML systems.
  • Experience with model deployment, inference, evaluation, and/or data pipelines.
  • Strong understanding of distributed systems and system reliability.
  • Ability to write clean, maintainable, production-quality code.
  • Comfortable working in ambiguous, fast-moving environments.

Nice to Have

  • Ownership mindset with bias toward experimentation and continuous improvement.

Outcomes

  • AI infrastructure reliably supports production workloads at scale.
  • Models can be trained, evaluated, deployed, and improved efficiently.
  • Inference meets targets for latency, throughput, reliability, and cost.
  • ML pipelines are reproducible, observable, maintainable, and robust, with quick diagnosis of regressions.
  • Reusable platform primitives accelerate building new AI products.

About Bjak

Bjak (described as building “A1”) is creating an AI assistant for everyday users, aiming to bring intelligence to conversations, errands, and workflows with minimal prompting. The product emphasizes reliability for long-running workflows, persistent context, multi-step reasoning, and successful real-world task completion. The company is focused on scalable, cost-efficient production systems for AI capabilities.

Scraped 8/15/2026