AI Research Scientist

Fuse Energy; New York (NY); On-site; USD 150,000 - 210,000; Full time

Benefits offered by this job

Competitive equity

Biannual bonus scheme

Fully expensed tech gear

Private health insurance

Breakfast and dinner allowance

Job summary

Fuse Energy is pursuing ambitious AI research to power an Energy Foundation Model that unifies generation, grid, demand, weather, and price forecasting. The role focuses on pre-training the model, defining inputs and training objectives, and validating improvements with rigorous experiments and backtests.

You will work with our quants and software engineers to translate research into production, leveraging household-level data while protecting privacy.

Qualifications

• Do the pre-training research for the Energy Foundation Model.
• Design the architecture, inputs and training objectives for one model across generation, grid, demand, weather and price data.
• Run pre-training experiments and find what actually improves results.
• Write up findings as research, and work with quants and engineers who take the model into production.

Responsibilities

• Do the pre-training research for the Energy Foundation Model.
• Design the architecture, inputs and training objectives for one model across generation, grid, demand, weather and price data.
• Run pre-training experiments and find what actually improves results.
• Build rigorous evaluations and honest backtests, with calibrated uncertainty.
• Train on household-level data without leaking personal information.
• Write up findings as research, and work with our quants and engineers who take the model into production.

Skills

Pre-training research

Model architecture design

Experimentation & backtesting

Cross-functional collaboration

Job description

Fuse Energy is an energy startup on a mission to make energy abundant and affordable, fast. We combine first-principles thinking with cutting-edge technology to build a radically better energy system.

We've raised over $200M from top-tier investors including Balderton, Lakestar, Accel, Creandum, Lowercarbon, Ribbit, 20VC, Hummingbird and Collaborative Fund, alongside strategic angels including Nico Rosberg and GPs behind Meta, Revolut, Spotify and Uber.

We're building a fully integrated energy company: developing our own solar, batteries and other generation projects, building our own hardware, improving and developing grid infrastructure, trading power in real time, using AI across the business, and installing distributed energy in homes. By selling directly to consumers we cut out the middleman, lower costs and pass the savings on to our customers.

As an AI Research Scientist, you will do the pre-training research behind the Energy Foundation Model: one model, trained on generation, the grid, demand, weather and price together, that learns the relationships between them that a human analyst would never think to write down. Today we model each forecasting problem separately; you will work out how a single model should be built and trained, and show that it works. We have data nobody else can buy, including household-level consumption from hundreds of thousands of UK homes, which outside trading firms cannot get. The work is research: experiments, evidence and papers that shape how we forecast, hedge and trade.

Requirements

• Do the pre-training research for the Energy Foundation Model
• Design the architecture, inputs and training objectives for one model across generation, grid, demand, weather and price data
• Run pre-training experiments and find what actually improves results
• Build rigorous evaluations and honest backtests, with calibrated uncertainty
• Train on household-level data without leaking personal information
• Write up findings as research, and work with our quants and engineers who take the model into production

Benefits

• Competitive salary and eligibility for equity
• Biannual bonus scheme
• Fully expensed tech to match your needs
• Private health insurance
• Breakfast and dinner allowance for office-based employees

As we hire globally, benefits vary by location.