Wayfair - Senior Software Engineer - MLOps

Responsibilities :

- Operationalize and deploy machine learning models built by Data Science teams using robust MLOps practices, including CI/CD pipelines, model versioning, monitoring, and rollback strategies, Feature Engineering, orchestrate ETL processes, manage data processing pipelines, and automate machine learning workflows.

- Manage model deployment lifecycles, ensuring production-grade reliability, scalability, and observability of model-driven services integrated into communication decisioning systems.

- Design and build large-scale communication and personalization platforms that deliver intelligent, event-driven notifications across channels (email, push, SMS, chat) with sub-second latency and enterprise-grade reliability.

- The architect distributed backend services and microservices for campaign orchestration, lead ingestion, customer personalization, and communication governance, ensuring extensibility, observability, and high throughput across millions of daily interactions.

- Build event-driven systems using Kafka and real-time data streams, powering automated messaging, feedback loops, and decisioning workflows.

- Develop and maintain scalable RESTful APIs and Spring Boot-based microservices, enabling integration across marketing automation systems, customer data pipelines, and external vendors.

- Implement orchestration and workflow frameworks that ensure robust communication between asynchronous systems connecting campaign logic, customer events, and ML-based decision engines.

- Enhance platform reliability and observability by building monitoring dashboards, SLA enforcement metrics, and automated anomaly detection for throughput, latency, and deliverability.

- Collaborate cross-functionally with Product, Data Science, and Marketing to define requirements, ensure system interoperability, and drive measurable impact in engagement and conversion.

- Raise technical excellence by promoting best practices in backend architecture, distributed system design, API lifecycle management, and continuous integration/deployment.

Requirements :

- Experience with high-scale backend platforms and distributed systems.

- MLOps and Model Deployment Experience (Mandatory).

- Hands-on experience with model deployment, operationalization, and ML service lifecycle management.

- Bachelor's or Master's degree in Computer Science, Software Engineering, or related technical discipline.

- 10+ years of experience building high-scale backend platforms and APIs for data-intensive or event-driven systems.

- Mandatory : Deep expertise in MLOps, including model deployment, pipeline automation, monitoring, feature engineering, ETL frameworks, and scaling of ML services in production.

- Experience deploying and maintaining ML or rule-based decision systems built by Data Science teams.

- Strong command of Java (Spring Boot) and working knowledge of Python or Go, with a deep understanding of object-oriented design, concurrency, and multithreaded programming.

- Strong command of stream processing frameworks (Flink, Spark Streaming) or Pub/Sub architectures.

- Expertise in Kafka (topics, partitions, consumer groups, schema management) and event-driven microservices design.

- Proven experience developing RESTful APIs and microservices with Spring Boot, including authentication, routing, and observability integration.

- Strong background in cloud-native application design, deploying and managing workloads on GCP, AWS, or Azure, leveraging Docker and Kubernetes for containerization.

- Solid foundation in data modeling, SQL/NoSQL databases, and high-performance data access patterns.

- Strong problem-solving, debugging, and optimization skills with an emphasis on scalability, fault tolerance, and SLA-driven reliability.

- Familiarity with observability tools (Datadog, Grafana) and distributed tracing for root-cause analysis.

- Ability to mentor engineers, perform design/code reviews, and lead technical discussions across multiple workstreams.

- Excellent communication and collaboration abilities across engineering, product, and analytics teams.

Nice to Have :

- Experience with LLM or GenAI applications (e. g., prompt orchestration, ranking pipelines, or creative optimization systems).

- Exposure to campaign management, notification orchestration, or template-based content systems.

- Experience building multi-channel messaging systems (email, push, chat, SMS) with high concurrency and low latency.

- Knowledge of A/B testing infrastructure, experimentation frameworks, and message-governance pipelines.

- Background in config-driven workflow automation, feature flagging, or API gateway management.