Machine Learning Engineer

Middesk is a company transforming business identity verification with AI-driven applications. They are seeking a hands-on Machine Learning Engineer to take ownership of the ML lifecycle and collaborate with cross-functional teams to develop impactful ML solutions.

Responsibilities:

• End-to-end ML ownership: Lead the full lifecycle of ML systems — feature engineering, model design, training, evaluation, deployment, monitoring, and iteration
• Collaborate with a strong team: Work alongside data engineers, platform engineers, and product teammates who ensure you have the infrastructure, data, and context to deliver
• Design & deploy production models: Build high-performance ML applications in risk, fraud, trust & safety, and compliance domains
• Keep models healthy in production: Proactively monitor, detect drift, and retrain to ensure long-term performance and reliability
• Experiment & learn: Drive online experiments, offline evaluation, and counterfactual analyses to prove impact
• Shape ML foundations: Contribute to the feature store, model management, training/serving pipelines, and best practices that scale ML across multiple use cases

Requirements:

• 7+ years applied ML experience with proven impact in risk, fraud, trust & safety, compliance, fintech, or other high-stakes domains
• Track record of owning ML models end-to-end — from research and design to deployment, monitoring, and retraining in production
• Strong software engineering skills (Python, ML frameworks, deployment pipelines) and ability to write reliable, production-grade code
• Hands-on experience with ML infrastructure such as feature stores, model management, training/serving pipelines, and monitoring tools
• Comfortable as a senior IC: you can set technical direction, establish best practices, and mentor peers while collaborating effectively across teams
• Experience working cross-functionally with data engineers, platform engineers, and product stakeholders to bring ML systems to life
• Deep expertise in classification challenges such as imbalanced labels, sparse signals, cold start, and production version management
• B2B SaaS experience, ideally building ML products for enterprise customers
• Familiarity with graph, LLM-based feature generation, or AI agent workflows
• Experience scaling ML across multiple products or risk domains