Senior Engineering Manager (MLOps)
Posted Updated
Description
- We are seeking a Senior Engineering Manager, MLOps to join our growing team
- Thriving in an environment of rapid growth and ambiguity, you make high-judgment decisions on “build vs. buy” and prioritize technical roadmaps that align directly with e-commerce business outcomes
- Above all, you are energized by a culture of distributed decision-making and extreme candor, where you will lead a high-performing team to set new standards for how AI is industrialized at scale to serve Quince customers
- Define the MLOps Vision & Strategy: Architect a long-term roadmap that transitions ML workflows from manual scripts to a fully automated, self-service platform for all Quince Data Scientists and AI Researchers
- Own the “Paved Road” for Production: Build and maintain the end-to-end infrastructure for model training, deployment, and serving, ensuring researchers can move from “idea to production” with zero friction
- Drive Strategic Prioritization: Partner with business leaders to align infrastructure investments with core e-commerce drivers like real-time personalization, dynamic pricing, and inventory forecasting
- Lead “Build vs. Buy” Evaluations: Make high-judgment decisions on when to leverage cloud-native services (e.g., SageMaker, Vertex AI) versus building custom internal tools to optimize for cost, speed, and flexibility
- Guarantee System Scalability & Reliability: Oversee the uptime and performance of production ML services, ensuring the stack can handle massive traffic surges and seasonal spikes without degradation
- Manage Compute Governance & Costs: Direct the optimization of high-cost computational resources, such as GPU clusters and cloud instances, balancing high-performance training needs with fiscal responsibility
- Recruit and Mentor Top Talent: Build and lead a high-performing team of ML Infra and DevOps engineers, providing technical coaching, career pathing, and performance management
- Establish MLOps Standards: Drive the adoption of best practices in CI/CD for ML, Infrastructure as Code (IaC), and automated testing to ensure a modular and maintainable system
- Bridge the Research-Engineering Gap: Act as the primary cross-functional lead, translating the complex needs of AI Researchers into actionable engineering requirements for the infrastructure team
- Define and Track Velocity Metrics: Establish KPIs for the infrastructure team, such as model deployment frequency, mean time to recovery (MTTR), and infrastructure cost per inference
- Champion Operational Excellence: Lead root-cause analyses (RCAs) for production failures and foster a culture of accountability where systemic fixes are prioritized over “quick patches.”
- Stay Ahead of the AI Curve: Monitor emerging trends in LLM-ops, vector databases, and real-time feature engineering to ensure Quince’s infrastructure remains competitive and future-proof
- The ideal candidate is a technical visionary with a proven track record of building and scaling the underlying infrastructure that powers production-grade Machine Learning
- You have a deep understanding of the ML lifecycle—from model development and distributed training to automated deployment and real-time monitoring—and you are passionate about treating infrastructure as a product for your “customers”: Quince’s Data Scientists and AI Researchers
- You are a self-starter who excels at identifying architectural bottlenecks and transforming them into seamless, automated “paved roads” that increase team velocity without sacrificing stability
- Experience partnering with AI Research and Data Science teams to understand their unique workflows and translate research needs into robust, scalable engineering solutions
- Expertise in building and managing Feature Stores and high-throughput data pipelines (using tools like Spark, Flink, or Kafka) to ensure data consistency across training and serving
- Deep technical expertise in cloud-native infrastructure (preferably AWS) and orchestration tools like Kubernetes (EKS), Docker, and Infrastructure as Code (Terraform/Pulumi)
- Kindness and high standards: You move fast and push for excellence, but you do so as a supportive team player who fosters a culture of psychological safety and extreme candor
- A product-oriented mindset, with the ability to treat infrastructure as a platform and prioritize the roadmap based on researcher velocity and business ROI
- 10+ years of industry experience, with at least 3-5 years in a leadership or management role specifically focused on ML Infrastructure, MLOps, or large-scale Data Platform engineering
- Proven track record of building and scaling MLOps platforms that support the full model lifecycle—from data ingestion and distributed training to real-time inference and monitoring
- Hands-on experience with ML frameworks and tooling, such as PyTorch, TensorFlow, Kubeflow, or SageMaker, and a strong opinion on how to integrate them into a cohesive developer experience
- Exceptional communication and influence skills, capable of navigating ambiguity and building consensus across engineering, product, and data science leadership
- Excellence in operational leadership, with a history of driving service availability, performance, and stability through rigorous on-call rotations and root-cause analysis
- Strong understanding of CI/CD for ML, including automated testing for models, model versioning, and “blue-green” or “canary” deployment strategies
- Demonstrated ability to manage high-cost compute resources, with experience optimizing GPU utilization and cloud spend in a hyper-growth environment
Skills
- AI
- AWS
- CI/CD
- Cloud
- Cloud Native
- Data Ingestion
- Data Pipelines
- Data Science
- Developer Experience
- DevOps
- Distributed Training
- Docker
- E-commerce
- EKS
- Feature Engineering
- Flink
- GPU
- Infrastructure as Code
- Kafka
- Kubeflow
- Kubernetes
- LLM
- Machine Learning
- MLOps
- Model Deployment
- MTTR
- Performance Management
- Pulumi
- PyTorch
- Root Cause Analysis
- SageMaker
- Spark
- TensorFlow
- Terraform
- Test Automation
- Vector Databases
- Vertex AI
Sign in to read and join the discussion.