*Sponsorship is NOT available for this position.
Conceive and implement data processing algorithms in both post-processing (cloud based) and edge-computing environments. Develop tools to generate value added data products from large, spatially distributed and often discontinuous datasets derived from direct measurements using modern machine learning approaches. Develop and implement predictive algorithms to gap fill and future-cast timeseries data for meteorological, agricultural, and greenhouse gas monitoring applications. Develop spatially explicit tools to aggregate, analyze, and present datasets from diverse scientific fields. Work closely with subject matter experts to understand relevant scientific and engineering questions to be addressed. Serve as the subject matter expert in statistical analysis, machine learning and artificial intelligence theory. Keep up to date on new and novel tools and theoretical advancements that can strengthen and grow LI-COR’s market position.
Responsibilities
- Proactively explore and propose added-value data products that can be extracted, also using ML and AI technologies, from field measurements collected by networks of instruments.
- Interact with scientists and other end users to explore solutions and co-developments.
- Perform post-processing data analysis using datasets from LI-COR systems to evaluate performance and diagnose issues.
- Proactively explore, develop and test models to improve instrument and system performance based on experimental results.
- Manage statistical analysis code using source repository tools such as Gitlab.
- Write and test production quality code for on-board data processing (edge-computing) within instruments, in either OS (Linux) or microcontroller environments.
- Write and test production quality code for post-processing data analysis and synthesis tools.
Qualifications
Education
- Bachelor’s degree in applied statistics, data science, or applied mathematics preferred. Bachelor’s degree in science, technology, engineering or math (STEM) field with an emphasis on algorithmic development, signal processing, and data analysis will be considered.
Experience
- Minimum of three (3) years of post-graduate academic or commercial experience in analyzing large data sets.
- Fluent in data analytics tools for science and engineering applications. Python or R fluency required. Matlab or C/C++ experience a plus.
- Experienced with Machine Learning (ML) and Artificial Intelligence (AI) theory and related software tools.
- Experience with geographic information systems (GIS) a plus. Examples include ArcGIS and Google EarthEngine.
- Demonstrated ability to synthesize new algorithms for data analysis and presentation.
- Experience with implementing data processing for embedded systems and familiarity with edge computing a plus.
- Practical experience in related scientific field (micrometeorology, plant physiology, greenhouse gas monitoring, etc.) a plus.
- Experience with code repository tools such as Git (Gitlab, Github) a plus.
- Experience using cloud technologies on AWS, GCP, and/or Azure a plus. Examples include S3, Redshift, Sagemaker.