Loon · 16 hours ago
2026 PhD Residency, Machine Learning for the Electric Grid (Tapestry)
Mountain View, CA
Full-time
Onsite
New Grad
$109K/yr - $150K/yrLoon's Tapestry is an innovative project at the intersection of AI and the electric grid, focused on creating advanced analytical tools for energy management. As a PhD Resident, you will engage in applied machine learning research to enhance the reliability of energy data pipelines, collaborating with experts to develop and validate models for complex energy systems.
AerospaceInformation ServicesInternetTelecommunicationsTravel
Responsibilities
Design and evaluate Graph Neural Network (GNN)–based approaches for state estimation and data validation in power systems
Explore methods for cleaning, validating, and modeling noisy SCADA and industrial time-series data
Adapt and extend academic research into practical prototypes, benchmarking models against power system simulation tools (e.g., pandapower, MATPOWER)
Analyze model performance under real-world data challenges such as missing measurements, sensor failures, and outliers
Collaborate closely with machine learning researchers and domain experts to iterate on approaches and share findings
Clearly document results and communicate insights to inform future research and product development
Qualification
Required
Currently enrolled in a PhD program (or a Master's program with equivalent research experience) in Computer Science, Electrical Engineering, Machine Learning, or a related quantitative field
Demonstrated research experience in applied machine learning or deep learning
Hands-on experience with Graph Neural Networks (GNNs) and modern deep learning frameworks (e.g., PyTorch, JAX)
Strong programming skills in Python and familiarity with common data science libraries
Strong written and verbal communication skills, with the ability to explain complex technical concepts clearly
A strong interest in decarbonizing the electric grid and building a more sustainable energy future
Preferred
Familiarity with streaming or real-time machine learning systems
Experience with power system modeling, state estimation, power flow, or simulation tools such as pandapower or MATPOWER
A track record of translating research ideas into working machine learning prototypes
Publications in top-tier machine learning or energy-focused conferences (e.g., NeurIPS, ICML)
Experience working in a startup or high-growth research and development environment
Benefits
Medical, dental, and vision coverage
Competitive residency stipend and housing relocation support for the duration of the program.
Direct mentorship from industry-leading research scientists and engineers.
Opportunity to work on "moonshot" problems with access to Alphabet-scale compute and resources.
Company
Loon
Loon is a network of high altitude balloons used to provide stable internet coverage on the ground. It is a sub-organization of Alphabet.
Founded in 2011
51-200 employees
H1B Sponsorship
Loon has a track record of offering H1B sponsorships. Please note that this does not
guarantee sponsorship for this specific role. Below presents additional info for your
reference. (Data Powered by US Department of Labor)
Distribution of Different Job Fields Receiving Sponsorship
Represents job field similar to this job
Trends of Total Sponsorships
2021 (9)
2020 (12)
Funding
Current Stage
Growth StageTotal Funding
$125MKey Investors
HAPSMobile
2019-04-25Undisclosed· $125M
Recent News
2025-10-31
Company data provided by crunchbase