About the Role:
We are seeking a talented and driven Machine Learning Optimization Engineer to join our innovative team. This role is crucial for turning innovative prototypes into scalable, production-grade solutions. You’ll be responsible for transforming our cutting-edge machine learning models into highly efficient, high-performance applications ready for real-world deployment. If you’re passionate about squeezing every last drop of performance out of ML models, this is the role for you!
Key Responsibilities:
- Analyze and profile machine learning models to identify performance bottlenecks in terms of latency, throughput, and computational cost.
- Apply state-of-the-art optimization techniques, including but not limited to quantization, pruning, knowledge distillation, and architecture modification, to meet performance targets (e.g., reduce inference latency by 30% for cost reduction).
- Benchmark model performance across various hardware platforms to ensure optimal cost-efficiency and runtime.
- Compile and deploy optimized models to specialized hardware and cloud services, such as AWS Neuron (using AWS Inferentia) and AWS SageMaker.
- Deploy and maintain robust MLOps workflows for automated model optimization, deployment, and monitoring, using tools like MLflow, Kubeflow, or Airflow.
- Work with containerization tools like Docker to ensure reproducible and scalable deployments.
- Collaborate closely with ML researchers and ML Engineers to understand model architecture and ensure seamless integration into production pipelines.
- Stay current with the latest research and industry trends in model optimization and efficient deep learning.
Qualifications:
- Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field.
- Proven experience in optimizing and deploying machine learning models in a production environment.
- Deep understanding of computer architecture, including memory hierarchy, parallelism, and hardware-specific features (e.g., NVIDIA Tensor Cores, AWS Inferentia) to optimize ML models via hardware-targeted code for efficient deployment.
- Strong proficiency in Python and deep learning frameworks such as PyTorch.
- Hands-on experience with model optimization libraries and tools (e.g., ONNX Runtime, TensorRT, TVM).
- Solid understanding of ML model architectures (e.g., Transformers, CNNs) and their computational characteristics.
- Direct experience with cloud platforms, particularly AWS and services like SageMaker, EC2, and S3.
- Excellent analytical, problem-solving, and prioritization skills.
- Strong communication and presentation skills.
- Resourceful, ability to work independently while balancing being part of a team.
- Ability to use Gsuite tools in their work.
- A strong portfolio of personal projects demonstrating your AI/ML skills (e.g., GitHub repositories, publications, conference presentations) is highly desirable.
Bonus points:
- Specific experience deploying models to AWS Neuron and using the Neuron SDK.
- Familiarity with hardware accelerators for ML (GPUs, TPUs, AWS Inferentia/Trainium).
- Experience with lower-level programming languages like C++ for performance-critical code.
- Proficiency with containerization technologies like Docker and orchestration systems like Kubernetes.
- Knowledge of compiler technology and how it applies to machine learning models.
At CubiCasa, we offer you
- A meaningful and cutting-edge mission statement: “We will empower the world to attach a Floor Plan on every listing”.
- A dynamic and a supportive workplace for tomorrow’s superstars.
- The flexibility to choose when and where you work, so you can shape your work in the way that fits you best, but we still hope to see you from time to time at our office in Helsinki or Oulu.
- Competitive salary (negotiable) and all the tools needed to do your work
- Attractive package of benefits incl. lunch, well-being, bike benefit
- Wide healthcare service
How to Apply:
Please send your resume and a cover letter explaining, why you are the ideal candidate for this position via our career page. Apply at the latest on Sunday November 23, 2025.
Join us in shaping the future of virtual home touring. We look forward to hearing from you!