Machine Learning Platform Engineer
Bjak · Remote · Germany ·
COMPENSATION
€•• – ••k
Listed on the employer's job board (Ashby)
- Fully remote
- ML Platform Engineering
- Python + PyTorch
- GPU infrastructure
- Distributed systems
ActAI is building proactive, AI-native applications that reduce the need for complex prompting. As an ML Platform Engineer, you will design and operate the systems behind their AI stack, covering everything from model training to production observability. You will work with AI engineers and researchers to turn models into reliable, cost-efficient production systems.
What you'll do
- Build and operate ML infrastructure powering AI products
- Design systems for model training, evaluation, and deployment
- Optimize model serving for high-throughput and low-latency
- Develop pipelines for data preparation and continuous improvement
- Create tooling to help teams experiment and ship models faster
- Build evaluation infrastructure to measure model quality
- Implement monitoring, tracing, and alerting for ML workloads
- Identify bottlenecks and improve system performance continuously
What you'll need
- Strong software engineering fundamentals
- Experience building production ML infrastructure or platforms
- Knowledge of model deployment, inference, and data pipelines
- Understanding of distributed systems and reliability
- Ability to write clean, maintainable production code
- Comfortable working in ambiguous, fast-moving environments
- Bias toward ownership and continuous improvement
Stack
- Python
- PyTorch
- JAX
- vLLM
- SGLang
- TensorRT-LLM
- Cloud infrastructure
- Distributed systems
- Vector databases