Intuition Robotics is a VC backed startup developing cognitive AI social agents and products (e.g. ElliQ) that is changing how people and machines interact. The company was founded in 2016 and is based in Israel with offices in San Francisco, CA. Intuition Robotics has raised over $58M in funding and is supported by renowned industry experts. Some of our key investors include Toyota, Samsung Next, iRobot and more.
Responsibilities:
- Creating high level audio based perception models such as: Audio based event classification, VAD, Silence detection, TV detection, ASR, speaker recognition
- Responsible for all the ML pipeline: Problem definition, evaluation metrics, dataset creation, data cleaning, feature creation and selection, model development, benchmarking, visualizing and communicating the results, model serving and production readiness
- Developing the models to both the cloud and low resources environments
- Deep understanding of the Audio field, following the state of the art methods
- Generating quick POC for project evaluations
- Combining the audio based models with the other perception modalities (such as computer vision) to create better overall perception
Requirements:
- M.Sc or Ph.D Involving machine learning or related research
- Proven experience in implementing audio based algorithms to solve real world problems (advantage – experience from the industry)
- Proven experience with machine learning and Deep Learning frameworks and methodologies
- Strong understanding and experience with digital audio signal processing
- Experience with scientific programming languages such as Python or Matlab
- Self-starter, independent and innovative
Advantages:
- Developing models in a low resources environment (smart phones, IOT etc.)
- Develop robust algorithms for integrating multiple sensors and modalities
- Experience with Machine Learning applied to Audio Processing and Synthesis, or Audio-Visual Learning
