23 hours ago
Base Salary
$209k - $217k/yr
Responsibilities
- Define the standard architecture for Java services calling ML models, including client libraries, API contracts, latency budgets, and fallbacks.
- Set and implement standards for load testing, performance benchmarking, capacity planning, reliability, monitoring, lifecycle management, and SLOs for model-integrating services.
- Lead profiling, JVM tuning, caching, request batching, concurrency, and other performance improvements for high-traffic model integrations.
- Lead complex ML architecture and delivery work spanning multiple teams and systems, including reusable pipelines and deployment patterns.
- Own model architecture and tuning for demanding deployments while balancing accuracy, latency, scalability, and cost.
- Run design and code reviews, make cross-team architecture decisions, own the technical roadmap, and mentor engineers.
- Partner with Applied Scientists, data and infrastructure platform teams, engineering leadership, product stakeholders, and executives.
Requirements
- BS, MS, or PhD in Computer Science, Engineering, Mathematics, Statistics, or a related field, or equivalent experience.
- 8+ years of professional software engineering experience with deep expertise building and operating high-traffic Java backend services.
- 5+ years building and running production ML systems, including 3+ years at senior scope setting technical direction across teams or systems.
- Expert Java and object-oriented design skills, including Spring Boot or similar service frameworks, gRPC APIs, and JVM performance tuning.
- Experience with load testing and performance standards using Gatling, JMeter, or similar tools, plus capacity planning for changing service loads.
- Experience designing highly available distributed systems with automated testing and monitoring.
- Deep production ML architecture experience spanning training pipelines, batch and real-time serving, feature pipelines, model versioning, and rollback.
- Strong Python and hands-on model development experience with XGBoost, LightGBM, PyTorch, or TensorFlow.
- Strong data engineering skills in Spark and SQL, including streaming or batch pipelines.
- Experience with AWS or GCP, SageMaker, Vertex AI or equivalent, Docker, and Kubernetes.
- Experience with experimentation, A/B test design, guardrail metrics, and evaluating offline metrics.
- Proven technical leadership across ML and software engineering teams, including architecture reviews, influence without direct authority, and mentoring senior engineers.
- Clear communication of model behavior and technical trade-offs to technical and non-technical audiences, including executives.
- Preferred experience includes marketplace, e-commerce, or logistics systems; serving models alongside JVM services; internal ML platforms; Cassandra or other distributed NoSQL databases; Kafka or Flink; and cloud ML platform migrations.
Benefits
- Competitive compensation package with equity and a 401(k).
- Medical, dental, and vision plans, company-paid short- and long-term disability coverage, paid time off, paid vacation for non-exempt employees, paid sick leave, and paid parental leave.
- Discounted meals and exclusive perks across the Wonder family of brands.
- Hybrid work requiring 3 days per week in the office, with the option to work in the office up to 5 days per week; this role is listed for New York.
- Benefits eligibility, effective dates, and plan options vary by employment classification and location.
Tech Stack
Apache CassandraApache FlinkApache JMeterApache KafkaApache SparkAWSDockerGoogle Cloud PlatformgRPCJavaKubernetesLightGBMPythonPyTorchSpring BootSQLTensorFlowXGBoost
Categories
About Grubhub
Grubhub builds an online marketplace and logistics network for ordering takeout and delivery from local restaurants across the U.S. It earns commissions and delivery fees, and offers consumer subscriptions and corporate solutions. Founded in 2004 and headquartered in Chicago, it is part of Wonder Group and lists hundreds of thousands of merchants across 4,000+ cities.