Principal ML Engineer

Overview

Prodege is a cutting‑edge marketing and consumer insights platform helping leading brands, marketers, and agencies uncover answers to business questions, acquire new customers, increase revenue, and drive brand loyalty. With a major investment from Blackstone in Q12026, Prodege is focusing on growth and innovation to empower partners to gather meaningful, rich insights and better market to target audiences. This role focuses on shaping machine learning across Prodege’s Performance Marketing business.

• Own the architecture and delivery of offline/online ML systems, feature pipelines, inference patterns, feedback loops, and monitoring.
• Lead the design, build, and evolution of production ML algorithms and systems that drive real business outcomes.
• Personally drive critical implementations, proving out new approaches in production before scaling them across the team.
• Architect and ship scalable ML systems across offline training, online inference, feature pipelines, feedback loops, and model monitoring.
• Build and evolve solutions across ranking/recommendation, rewards optimization, ROAS/LTV prediction, campaign and offer optimization, experimentation, and decisioning.
• Establish robust experimentation and measurement frameworks, including offline evaluation, A/B testing, KPI design, and post‑launch validation.
• Make key decisions on MLOps, tooling, infrastructure, serving patterns, observability, and platform architecture.
• Partner closely with Data Engineering, BI, Product, Engineering, and business teams to create reliable data foundations and connect ML work to business priorities.
• Drive an AI‑first mindset by using AI to accelerate research, prototyping, feature engineering, experiment analysis, debugging, documentation, and developer productivity.
• Mentor ML engineers and data scientists by leading through direct contribution and raising the bar on model quality, technical judgment, and engineering rigor.

• Offline and online ML systems, feature pipelines, inference patterns, feedback loops, and monitoring.
• End‑to‑end ML systems spanning feature generation, training, inference, experimentation, monitoring, and lifecycle management.
• Production ML algorithms and decision‑ing systems across ranking, rewards, ROAS/LTV, personalization, and offer optimization.
• Experimentation frameworks that connect model performance to business outcomes.
• Production‑grade standards across MLOps, observability, retraining, governance, and reliability.
• Hands‑on technical leadership for the ML team through direct contribution, code reviews, and mentoring.
• The evolution of ML toward a more AI‑first way of working.

• Directly shape how ML drives revenue, margin, and user value.
• Work on analytically complex problems across ranking, rewards, ROAS, LTV, personalization, and optimization in a high‑scale AdTech/Mar Tech environment.
• Own ML from system design through production outcome, not just model development.
• Build on a real production data platform operating at scale: 50M daily events, 500M daily pipeline records, 100TB Iceberg lake, and 50
  
  Kafka topics.
• Inherit a strong experimentation culture with 30+ ML experiments per month, 10 live experiments already this year, and a feature‑rich data foundation with 1000+ features, including user and item embeddings.
• Build on real business momentum – the best ranking models are already outperforming prior models.
• Have principal‑level scope to influence both the systems being built and how the broader ML organization works.
• Help push the organization toward a more AI‑first engineering future.

• 8+ years of experience in software engineering, ML engineering, MLOps, or related technical fields.
• 5+ years building, deploying, and supporting production ML systems at scale.
• Strong experience in AdTech, Mar Tech, Growth, Performance Marketing, or adjacent domains.
• Hands‑on expertise in ranking, recommendation, rewards/incentives, ROAS/LTV prediction, personalization/optimization systems.
• Proven experience designing, shipping, and operating production ML systems end‑to‑end.
• Strong understanding of offline/online ML architecture,…