1 day ago
Base Salary
$240k - $250k/yr
Responsibilities
- Own the architecture of the ranking and recommendation stack, including candidate retrieval, multi-objective ranking, calibration, and conversion-versus-profitability optimization.
- Lead offline evaluation, online experimentation, and the evolution from short-term conversion optimization toward long-term diner value.
- Apply information retrieval and recommender-systems research, including LLM-based query understanding, embedding retrieval, sequential user representations, and real-time inference.
- Set technical direction across multiple teams and make cross-system design decisions spanning search ranking, recommendations, retrieval, and query understanding.
- Raise standards for model evaluation, scorecards, reproducible training pipelines, safe deployment, SLOs, observability, and technical-debt management.
- Partner with Product, Search Engineering, Ads, and Data Platform to shape roadmaps and ensure required data and infrastructure are available.
- Mentor senior and mid-level engineers, participate in hiring, and document technical decisions and trade-offs for technical and executive stakeholders.
Requirements
- Master’s or PhD in a quantitative discipline such as Computer Science, Mathematics, Physics, Engineering, or Statistics, or equivalent experience.
- 8+ years building and shipping machine learning systems, including 3+ years operating at staff-level scope.
- Deep production experience with recommendation systems, ranking, or information retrieval at scale under real latency and cost constraints.
- Proven production deep-learning experience with TensorFlow or PyTorch, including training, serving, and tuning GPU-based runtime models.
- Experience with large language models and transformer architectures, including fine-tuning, embedding generation, and latency-sensitive deployment.
- Strong data-engineering fundamentals with PySpark, Hive/SQL, the Python data stack, and debuggable feature pipelines.
- Experience designing A/B tests, selecting guardrails, and evaluating the limitations of offline metrics.
- Experience with cloud machine-learning infrastructure such as AWS or SageMaker, model deployment, production monitoring, and observability.
- Demonstrated technical leadership through mentoring, architecture reviews, cross-team influence, and decision-making without direct authority.
- Ability to communicate model behavior, performance metrics, and technical trade-offs to technical, non-technical, and executive audiences.
- Ability to follow current research and translate relevant findings into production systems, with a strong interest in continuous learning.
- Experience with language understanding over imperfect grammar, such as real-world search queries and menu or catalog text, is a strong plus.
Benefits
- Hybrid work requires 3 days per week in the office, with the option and encouragement to work in the office up to 5 days per week.
- Benefits include equity, 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, paid parental leave, discounted meals, and Wonder-family perks.
- Benefit eligibility, effective dates, and plan options vary by employment classification and location.
Categories
About Wonder
Wonder builds a mealtime platform that lets customers mix dishes from multiple restaurant brands in a single order, with options for dine-in, delivery, pickup, and meal kits. The New York-based, privately held company owns and operates its kitchens and technology and also develops robotic cooking systems used with enterprise B2B clients. Wonder expanded its portfolio by acquiring meal-kit pioneer Blue Apron in 2023.