Principal Machine Learning Engineer - Pricing in London

Who We Are: We are rebuilding the energy transaction, making it transparent and fair. Our goal is to put power back where it belongs, in the hands of customers and to take on one of the most critical problems of our century, access to low cost electricity. tem exists to fix a broken global energy market that’s long favoured legacy operators, intermediaries, and opaque pricing. Today’s electricity system was not designed for rapid decarbonisation, AI-driven efficiency or fair access for the actual users - businesses and generators. We’ve built the first AI native transaction infrastructure to reinvent how electricity is bought, sold and priced. Our technology is designed to cut out the inefficient fees, automate complex market flows, and bring transparency and fairness to energy transactions at scale.

The Role: Rosso is tem's core IP, the transaction infrastructure that prices electricity for thousands of businesses, balances portfolios in real time, and sits on the critical path for every deal tem closes. Machine learning is at the heart of Rosso, combining forecasting, optimisation and classical ML to process billions of data points and drive thousands of automated decisions a day. Every inference shapes the prices our customers see, so you can immediately see the impact of your work.

Responsibilities:

• Own the technical direction for pricing ML: Define what to build and how within the pricing engine, setting the strategy and roadmap for pricing machine learning as a core piece of tem's IP.
• Build ML systems for price optimisation: Design and implement models that dynamically set prices, balancing the trade‑off between signing probability, portfolio balance and margin maximisation.
• Solve imbalance problems: Develop probabilistic models to optimise risk management and short‑term balancing decisions in a highly dynamic environment.
• Bridge modelling and production: Own the modelling and data layer while working closely with software engineers and MLOps to ensure models are architected for production, contributing to system design decisions that affect performance and reliability.
• Communicate pricing decisions clearly: Articulate model behaviour, assumptions, and trade‑offs to other technical stakeholders so that pricing decisions are understood across the teams that depend on them.

Requirements:

• Must‑haves: Deep experience building ML systems for pricing, revenue optimisation, or decision‑making under uncertainty, with a track record of models that went from concept to production and delivered measurable commercial impact.
• Strong foundation in stochastic optimisation and probabilistic modelling, with the judgement to formulate ambiguous business problems as the right mathematical approach rather than reaching for familiar tools.
• Proven first‑principles reasoning: you choose between stochastic programming, classical ML, reinforcement learning, or a simple heuristic based on the problem, not the technique you know best.
• The engineering craft to match your modelling depth: production‑grade Python, a high bar for code quality and system design, and the ability to work alongside software engineers as a technical peer across the full ML lifecycle.
• Senior technical leadership in ML: a track record of setting direction for a significant technical area, influencing cross‑functional teams, and translating complex model decisions into clear terms for commercial, product, and engineering stakeholders so they are understood and acted on.

Bonus points:

• Experience with reinforcement learning or causal inference in applied, commercial settings.
• Familiarity with energy markets, power trading, or portfolio management.
• PhD or equivalent research depth in a quantitative discipline (statistics, applied mathematics, physics, operations research, or similar).
• Ability to reason about the trade‑offs between optimisation solvers (Gurobi etc) and gradient‑based ML methods (PyTorch etc), and the judgement to know when to reach for each.
• Experience working with high data throughput systems in production.

Interview Process: Our processes normally take around 2‑3 weeks from first call to offer - please let us know about any adjustments to timelines that may be required. First call with our Talent Team (30 mins). This is to understand your experience, motivations, and discuss the role in more detail. Behaviour Interview with our Head of Data (60 mins). This is your chance to really understand the role, the expectations, and ensure alignment on ways of working. Technical Interview with the Team (90 mins). You'll meet with potential peers in this session and work through a live technical exercise. Culture‑Add Interview with Stakeholders (45 mins). The final session will be with two cross‑functional stakeholders, and will explore how your values align with ours, and is designed to be a genuine two‑way conversation, your chance to understand what it's really like to work at tem.

We welcome applications from people of all backgrounds, experiences, and identities, including those that are traditionally underrepresented in the tech and energy sectors. If you’re excited about this role but not sure you meet every requirement, we’d still love to hear from you. Your unique perspective could be exactly what we’re looking for.