Overview

We are looking for an innovative AI Infrastructure Engineer to design and optimize the systems that power machine learning models for our robotics platforms. In this role, you will build and maintain the infrastructure that supports the training, deployment, and scalability of AI-driven solutions. You’ll play a critical role in ensuring that our perception, planning, and decision-making algorithms perform efficiently in real-time, enabling precise manipulation and seamless operation of our robotics systems.

Your Responsibilities

• Infrastructure:

  • Design and implement scalable AI pipelines for training, testing, and deploying machine learning models.
  • Build and maintain systems for large-scale data collection, processing, and storage.

• Optimization:

  • Optimize infrastructure to ensure low-latency inference for real-time robotic applications.
  • Develop tools to monitor, debug, and optimize AI performance in production environments.
  • Collaborate with AI researchers and engineers to streamline the integration of machine learning models.
  • Utilize containerization and orchestration tools like Docker and Kubernetes to manage AI workloads.

• Administration:

  • Work closely with robotics and software teams to align infrastructure with system requirements.
  • Ensure compatibility of AI systems with cloud platforms and on-premise deployments.
  • Document infrastructure architecture and provide guidance on best practices.

Qualifications

• Education and Experience:

  • Bachelor’s or Master’s degree in Computer Science from a reputable university, graduating with a GPA of 1.7 or better (German scale).
  • OR Minimum three years of full-time working experience with asynchronous, parallel ML serving frameworks such as Torchserve, vLLM, LMDeploy, NVIDIA Triton.
  • OR Extraordinary GitHub repository with at least 10 stars.

• Skills:

  • Exceptional skills in programming languages such as Python, Go, or Java.
  • Strong knowledge of frameworks like TensorFlow, PyTorch, or ONNX.
  • Experience with distributed computing frameworks like Apache Spark or Dask.
  • Hands-on experience with cloud platforms such as AWS, GCP, or Azure.
  • Familiarity with MLOps tools like Kubeflow, MLflow, or Airflow.
  • Experience with data storage solutions like S3, HDFS, or PostgreSQL.
  • Strong understanding of containerization tools (Docker) and orchestration systems (Kubernetes).

• Additional Skills / Nice to Have:

  • Knowledge of robotics systems and real-time constraints is a plus.

What We Offer

• Wellpass (gym membership)
• Free meals at the workplace
• Flexible working hours
• A motivated team and an open corporate culture
• Competitive compensation and excellent career development opportunities