Background

Doublepoint creates cutting-edge interaction technology for next generation user interfaces on smartwatches, TV’s and AR. Our smartwatch algorithms detect subtle hand gestures using generic smartwatch sensors which hasn’t previously been possible. However, to do so consistently on a wide range of gestures deployed into production, we will need to expand our Algorithm Team.

For this team, Doublepoint is looking for a Principal ML Engineer with time-series and leadership experience to join our Algorithm Team whose goal is to create our core product, the algorithm itself.

Responsibilities

As Senior ML Engineer, your role would be to implement as well as guide the model development work based on smartwatch sensors like the IMU and PPG sensors. This will likely including many of the following responsibilities:

• Design, implement, analyse and improve our flagship time-series gesture classification models.

• Define, request for, manage, and curate the required training data for our models.

• Define meaningful test sets and metrics to evaluate our models on, and maintain a thorough understanding of our model performance in aggregate and in detail.

• Design model architectures and apply miniaturization techniques specifically for running models on embedded smartwatch compute.

You may be leading others members of the team as well as implementing with them some of the following activities:

• Plan quarterly tech roadmaps as well as sprint goals.

• Write scalable ML development pipelines with ML Ops Engineers.

• Maintain clear documentation of ML pipelines and algorithms.

• Monitor model performance and address issues such as drift or underperformance in new environments

• Act as the technical lead, mentoring junior developers and guiding team direction.

You will work closely with other members across the company on the following:

• Lead the detailed definition of relevant gestures with user research team.

• Define next revisions of gesture detection sensor hardware with the hardware team.

• Author the data collecting instructions for our datasets together with the data collection team.

Skills

The candidate we are looking for must possess:

• 5 or more years of machine learning engineering experience in production, ideally in a real-time, time-series application and user-centred environment.

• Experience with Signal Processing.

• Deep understanding and proven track record with Machine Learning including supervised and unsupervised learning, deep learning, data augmentation, classification, and embedded deployment.

• Strong software engineering skills in Python, Pytorch, TensorFlow Lite, and familiar with scalable ML pipeline tools like Kubeflow, MLflow, Optuna, Hydra and CICD workflows.

Our ideal candidate would also possess:

• Familiarity with gesture detection and biosignals where data varies across users substantially.

• Familiarity with human computer interaction.

• Familiarity with Bayesian statistics.

• Familiarity with hardware sensors and embedded systems such as IMUs, PPG’s, ARM M4 processor architectures, and Tensorflow Lite.

Qualities

The other qualities we are looking for include:

• Strong collaboration skills to work effectively within and across teams.

• Clear communication to articulate complex ideas to technical and non-technical stakeholders.

• Adaptability to work on both high-level strategy and detailed implementation.

• The ability to foresee problems in advance based on experience and intuition and act on them effectively.

• High agency including taking initiative, owning challenges and one’s failures, and consistently delivers impactful solutions with minimal oversight.

Keywords

Machine Learning, Deep Learning, Signal Processing, Algorithm Engineer, Software Engineering, ML Ops, Sensors, Human Computer Interaction (HCI), Time Series

Hiring Process

1. Introductory Call and QnA with CTO Jamin Hu (30 mins)

2. Technical Interview with CTO Jamin Hu (45 mins)

3. Culture Interview with CEO Ohto Pentikäinen (30 mins)

4. Take-home challenge and review with Algorithm Team

5. Offer

6. Meet the team and get started