Principal MLE – Revenue Optimisation

This is a fully remote position, open to applicants in United Kingdom.

📋 Description

• Take charge of the technical vision for pricing machine learning. Determine the necessary developments and the approach to take. Establish the roadmap for the pricing engine as a vital component of the team’s intellectual property and ensure its performance is upheld.

• Accurately define and address the pricing challenge. The mathematical framework is not fully established yet. Your initial task is to create it: a dynamic, real-time system that optimizes for signing probability, portfolio balance, and margin simultaneously. Select the most suitable method—stochastic programming, reinforcement learning, classical ML, or a hybrid approach—based on the problem rather than prior experience.

• Develop and deploy models comprehensively. Take ownership of the modeling and data layers. Write production-quality Python code. Design models with deployment considerations and guide them into production—executing independently of engineering constraints.

• Address imbalance challenges. Create probabilistic models to enhance risk management and make short-term balancing decisions in a rapidly changing environment.

• Act as the advocate for pricing machine learning throughout the organization. Commercial, product, and engineering teams rely on this engine. They must grasp its functions and rationale. You will facilitate this understanding—clearly and accurately.

⛳️ Requirements

• Extensive experience in developing machine learning systems for pricing, revenue optimization, or real-time decision-making at organizations where pricing is central to the product, not merely a support function. Proven success with models that have gone into production and positively impacted commercial metrics.

• Strong grounding in stochastic optimization and probabilistic modeling. The ability to mathematically articulate ambiguous business challenges before selecting a tool.

• Reasoning from first principles across various methods. You will make informed choices between stochastic programming, reinforcement learning, classical ML, or straightforward heuristics based on the specific problem at hand.

• Engineering expertise that complements your modeling skills. You should produce high-quality, production-ready Python code and be capable of advancing models from concept to deployment without dependencies hindering progress.

• Proven senior technical leadership. A history of guiding a significant technical domain, influencing cross-functional teams, and translating intricate model behaviors into comprehensible terms for commercial, product, and engineering stakeholders, ensuring decisions are recognized and acted upon.

• Experience with real-time pricing at scale in sectors such as ride-hailing, food delivery, logistics, or similar fields where latency and portfolio effects are critical.

• Knowledge of energy markets, power trading, or portfolio risk management is advantageous.

• A PhD or equivalent research expertise in a quantitative field—such as statistics, applied mathematics, operations research, or related disciplines.

• Capability to evaluate trade-offs between optimization solvers (like Gurobi) and gradient-based methods (such as PyTorch), with the discernment to know when to utilize each option.

• Experience with causal inference or reinforcement learning in practical commercial environments.

🏝️ Benefits

• Offers Equity