Build intelligence for continental-scale energy systems while shaping Tapestry’s multi-year machine learning strategy. This hybrid role in San Francisco, CA offers a competitive USD 262,000 - 361,000 per year, along with equity and benefits designed to support long-term impact. You will work in an Alphabet-backed environment on production ML/AI systems that connect AI research with power-grid physics.
Why this role
You’ll architect machine learning systems that advance grid planning, simulation, and asset intelligence at scale. The work spans multimodal modeling, graph neural networks, geospatial and remote-sensing data, reinforcement learning for physical control, and multi-turn agentic systems. You will also set architectural patterns and production standards that improve reliability, performance, and long-term maintainability.
Responsibilities
- Own the technical roadmap and system architecture for Tapestry’s intelligence engines, scaling models across multimodal machine learning, graph neural networks, geospatial and remote-sensing data, reinforcement learning for physical control systems, and multi-turn agentic systems.
- Collaborate with machine learning technical leads, power systems scientists, software engineers, product managers, and global utility partners to turn large-scale grid data into actionable insights for planning, operations, and maintenance.
- Act as a technical force multiplier by mentoring senior and staff-level engineers, establishing rigorous production standards, and aligning cross-functional stakeholders around architectural direction.
- Advance state-of-the-art approaches across agentic AI, physics-informed ML, natural language understanding, and geospatial intelligence to solve highly constrained energy-infrastructure challenges in production environments.
- Establish scalable architectural patterns and technical standards that strengthen reliability, performance, and maintainability.
- Shape the long-term machine learning strategy using first-principles thinking, rigorous technical analysis, and clear decision-making across complex, evolving problem spaces.
Requirements
- Master’s degree or PhD in Computer Science, Electrical Engineering, Applied Mathematics, or a related quantitative field, or equivalent practical experience.
- 10+ years of professional experience building, training, and deploying large-scale machine learning systems in production, with deep proficiency in PyTorch, JAX, or TensorFlow.
- Proven experience architecting systems that handle massive datasets or highly compute-intensive, parallel workloads.
- Experience partnering across technical disciplines and functions, aligning stakeholders around complex architectural decisions, and mentoring senior technical leaders.
- Strong first-principles thinking and structured technical judgment for complex, ambiguous problems spanning machine learning, physical systems, and production infrastructure.
- Strong written and verbal communication skills, with the ability to explain complex technical concepts clearly to multidisciplinary audiences.
Technologies
PyTorch, JAX, TensorFlow, graph neural networks, geospatial data, remote-sensing data, agentic systems, natural language understanding, reinforcement learning.
Benefits
- Competitive salary and equity
- Medical, dental, and vision coverage
- Generous PTO and flexible hybrid work model
- 401(k) with employer contribution
- Professional development
- Work on important real-world problems within an Alphabet-backed environment
It’d be great if you also had
- Experience applying machine learning to physical, interconnected networks.
- 4+ years of professional experience working with grid modeling, simulation, state estimation, or power-system optimization, including familiarity with physical grid constraints, utility data structures, or spatiotemporal modeling for the grid.
- Familiarity with commercial grid-simulation software or numerical solvers, such as PSS®E, GridLAB-D, or MATPOWER, alongside scientific Python tools.
- A history of open-source contributions or peer-reviewed publications at leading AI conferences.
- Experience operating in a high-growth, or rapidly evolving technical environment.
Tapestry values
- Take charge: Take initiative and own outcomes that move the mission forward.
- Transform with purpose: Build solutions that solve real problems and create meaningful impact.
- Be a Tapestry, not a thread: Collaborate across diverse skills and perspectives.
- Always fine-tune: Stay curious, seek feedback, and refine understanding.
- Stay grounded: Listen openly, value different perspectives, and stay focused on what matters most.