Help & Supportcareers@gravityer.com
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Data Scientist at NASA's Jet Propulsion Laboratory
Machine learning ------------------ * Passionate about leveraging ML on problems in the humanitarian and development sphere * Experienced in classical, deep, and reinforcement learning * Comfortable with tools relevant to ML deployment and scaling including TensorFlow, Keras, Kubernetes and KubeFlow, cloud computing, Docker, and Git * Proficient in Python and experienced in C++, Matlab, and Java Research ---------- * Strong research background with a PhD in Neuroscience from University of Washington * Thesis work on advancing brain-computer interfaces to help people with brain damage * Passionate about blending basic knowledge from science with techniques from engineering
University of Washington
Doctor of Philosophy (PhD), Neuroscience
January 1, 2012 – January 1, 2017
Washington University in St. Louis
BS, Bioengineering and Biomedical Engineering
January 1, 2008 – January 1, 2012
NASA Jet Propulsion Laboratory
Data Scientist
March 1, 2020 – Present
Pasadena, California, United States
Development Seed
Machine Learning Engineer
November 1, 2017 – March 1, 2020
Washington DC-Baltimore Area
University of Washington
Postdoctoral Research Fellow
March 1, 2017 – September 1, 2017
University of Washington
PHD Graduate Student
September 1, 2012 – March 1, 2017
Center for Innovation in Neuroscience and Technology
Research Fellow
May 1, 2011 – August 1, 2011
St. Louis, Missouri
Washington University in St. Louis
Biomedical Engineer
August 1, 2008 – May 1, 2012
St. Louis, Missouri
Mapping Mars with A.I.
August 1, 2018 – Present
The volume of data returned by orbital imaging systems like the Context Camera (CTX) on the Mars Reconnaissance Orbiter (MRO) is overwhelming expert analysts. Mars is a popular target for exploration, so we need powerful analysis techniques to ensure that we take full advantage of today's data when planning tomorrow's missions. Machine learning (ML) algorithms may help scientists better capitalize on this flood of data because ML solutions readily scale on cloud computing infrastructure. We’re specifically using ML to assist scientists in identifying important surface features on Mars. Toward this goal, we're working with Arizona State university to use a supervised ML algorithm to geolocate and characterize craters across the surface of Mars. This approach could assist with landing and route planning on future Mars missions, improve geolocation algorithms that rely on matching craters (or other landform patterns), enable more accurate dating of geological features, and inform the solar system cratering rate. In this work, we use the You Only Look Once deep learning algorithm (Redmon and Farahi, 2018) to find and classify craters in CTX images. Preliminary results show that we can identify craters with diameters an order of magnitude smaller than manually-labeled crater databases (Robbins and Hynek, 2012). Our efforts are currently focused on mapping Jezero Crater, Midway, and NE Syrtis, the three candidate landing site for Mars 2020. In the near future, we plan to periodically apply this algorithm to all available CTX images and build a planet-wide crater map. In the long term, we hope to extend our algorithm to detect other surface features such as dunes, landslides and similar features such as recurring slope lineae, and small volcanic features.
Mapping the electric grid: Using ML to augment human tracing of high-voltage infrastructure
January 1, 2018 – April 1, 2018
Many people in the world still do not have access to electricity. In developing nations, this problem is especially acute as it limits participation in modern economy and culture. Improving the electric grid, however, is often logistically challenging in these regions because there is rarely a complete and accurate map of the existing electric infrastructure. This map is crucial as there is no way to make informed decisions on how to spend resources to improve the electric grid without it. Toward solving this problem, we built a pipeline to efficiently map the high-voltage (HV) grid at a country-wide scale. This pipeline relied on both machine learning (ML) and our Data Team -- a group of eight professional mappers. The ML component processed satellite imagery across an entire target country and returned geospatial locations likely to contain HV towers -- the tall metal structures that support HV lines running for hundreds or thousands of kilometers. Our Data Team then overlaid this information on top of satellite imagery and used it as a guide to help quicken their mapping of HV towers, lines, and substations. With this overlay, they could focus their attention on high priority areas and avoid the tedious task of reviewing entire countries worth of imagery by hand. Using this pipeline, we mapped nearly all of the HV network in Pakistan, Nigeria, and Zambia and found that our ML model increase mapping speed 33-fold per km^2 compared to a purely manual approach.
Cultural Fit Analysis
The candidate's projects, 'Mapping Mars with A.I.' and 'Mapping the electric grid,' demonstrate a strong interest in impactful, large-scale problems with societal and scientific relevance. This aligns well with organizations focused on innovation and real-world application of ML. The academic background (PhD, Postdoctoral Fellow) and experience at NASA JPL suggest a research-oriented and rigorous approach, which could be a good cultural fit for an advanced ML engineering role. The diversity of projects, from space exploration to humanitarian efforts, indicates a broad perspective and adaptability. However, the lack of explicit team collaboration details in the resume makes it difficult to fully assess cultural fit beyond project alignment.
Soft Skills & Operational Fit
The candidate's project descriptions demonstrate strong problem-solving skills, an ability to work on challenging, impactful projects, and a collaborative approach (e.g., working with Arizona State University, Data Team). The detailed explanations suggest good communication skills for technical concepts. However, without psychometric test results, a full assessment of work attitude, stress handling, and team collaboration is not possible.