Data Scientist
Avionyx Overview: Located in Northern California and multiple locations across the globe, the team at Joby Aviation is driven by our goal of creating an affordable, all-electric air transportation system. Avionyx S.A. is a software engineering services company based in Heredia, Costa Rica, fully owned by Joby Aviation. As an AS-9100D company and in business since 1989, Avionyx provides expert, high-quality, full-lifecycle avionics software and hardware engineering services for eVTOL/UAM, rotorcraft and fixed wing aircraft, complying with the most rigorous software engineering standards in the world. Job Overview:
Working as a Data Scientist in the Data Analytics team you will be responsible for developing analytical tools and reporting results from variety of datasets. You should be able to work cohesively with subject matter experts, understand both data systems and physical systems, and have an eye for anomalies in physical test data. A good dose of ingenuity is required when approaching a new dataset. You will also need to work closely with your colleagues across a broad set of highly technical disciplines who depend on data. The ideal candidate is energetic, has a positive attitude, is flexible and excited about learning and using new technologies.
Responsibilities: - Make sense of and groom data from a number of physical tests (aircraft, simulators, reliability test equipment, subsystem tests, etc.)
- Work closely with subject matter experts, engineers and developers to understand metrics of interest and compute them
- Generate dashboards for data visualization and clearly present the results
- Work with the data engineering team to develop and maintain efficient data pipelines
- Develop tools to make processing and reporting on data as consistent and easy as possible
- Leverage statistics, numerical fitting methods, and visualization tools to draw conclusions
- Develop algorithms to predict failures or the occurrence of certain events from the data
- Produce Machine Learning/Deep Learning models for automatic data labeling and anomaly detection
- Comfortable navigating a quickly changing environment and willing to learn on-the-fly to obtain and define requirements
- Contribute to LLM frameworks geared towards solving engineering problems.
- Bachelor’s degree or Master’s degree in computer science, engineering, math, physics, or similar field and 3+ years of related work experience
- Expert knowledge of Python and its numerical and data libraries (pandas, scipy, numpy, etc.)
- Work experience with Apache Spark or other big data tools
- Experience with data architectures in relation to how to store, fetch, and manipulate data (SQL, custom APIs, etc.)
- Used Git in small to medium size teams for code reviews
- Experience with large datasets visualization tools (matplotlib, seaborn, bokeh, plotly, Tableau, Looker, etc.)
- Experience with Machine Learning and Deep Learning techniques and associated libraries (TensorFlow, Keras, Sklearn, PyTorch, etc.)
- Experience with natural language processing and large language models
- Proficiency in statistical methods, A/B testing, hypothesis testing, etc.
- Work experience with anomaly/outlier detection in time series data
- Proficiency in other programming languages (Scala, R, SQL, Java, C, C++, etc.)
- Prior participation in data science competitions (Kaggle, etc.)
- Experience with automated testing (CICD)