Senior Staff Machine Learning Engineer

Wonder Group • New York, NY

3d • Hybrid

About The Position

Grubhub is seeking a Senior Staff Machine Learning Engineer to provide hands-on technical leadership for the machine learning systems behind Discovery, including ranking, recommendation, and retrieval systems used in search and the app experience. The role owns architecture across search ranking, homepage and topic recommendations, retrieval, and query understanding, ensuring that the connected systems work together effectively. It is an individual-contributor leadership role rather than a management position, working with staff engineers, product managers, and platform partners to set technical direction and improve how models are built, evaluated, and operated.

The engineer will lead end-to-end architecture for the ranking and recommendation stack, including candidate retrieval, multi-objective ranking, calibration, and the ensemble balancing conversion with profitability. The role also guides the shift from short-term conversion optimization toward long-term diner value, using offline evaluation and online experimentation to validate changes. Areas of technical focus include information retrieval and recommender systems, LLM-based query and intent understanding, embedding-based retrieval, sequential user representations, real-time inference, and production machine learning.

The role raises engineering and operational standards across teams through model evaluation, reproducible training pipelines, safe deployments, service-level objectives, observability, and proactive technical-debt management. It partners with Product, Search Engineering, Ads, and Data Platform, mentors engineers, participates in hiring, and communicates technical decisions and trade-offs to technical and executive stakeholders. The position uses a hybrid work model requiring three office days per week, with the option to work in the office up to five days per week.

Requirements

• MS or PhD in a quantitative discipline such as Computer Science, Math, Physics, Engineering, or Statistics, or equivalent experience.
• At least 8 years of experience building and shipping machine learning systems, including at least 3 years operating at staff-level scope across multiple teams, model families, or systems.
• Deep production experience in recommendation systems, ranking, or information retrieval at scale, under real latency and cost constraints.
• Track record with production deep learning in TensorFlow or PyTorch, including training, serving, and tuning runtime models on GPUs.
• Experience with large language models and transformer architectures, including fine-tuning, embedding generation, and deployment in latency-sensitive applications.
• Strong data engineering fundamentals, including PySpark, Hive/SQL, the Python data stack, and feature pipelines.
• Fluency in experimentation, including A/B test design, selecting guardrails, and assessing whether offline metrics are misleading.
• Experience with cloud ML infrastructure such as AWS/SageMaker or equivalent, model deployment, and production monitoring and observability.
• Demonstrated technical leadership through mentoring, driving design and architecture reviews beyond one's team, and influencing decisions without direct authority.
• Ability to communicate performance metrics, model behavior, and technical trade-offs to technical and non-technical audiences, including executives.
• Ability to follow research publications and synthesize findings into production systems.
• Strong interest in self-motivated continuous learning.

Nice To Haves

• Experience with language understanding over imperfect grammar, such as real-world search queries and menu or catalog text.

Responsibilities

• Own the end-to-end architecture of the ranking and recommendation stack, including candidate retrieval, multi-objective ranking, calibration, and the ensemble balancing conversion and profitability.
• Make cross-system design decisions spanning multiple models and systems.
• Lead the evolution of optimization objectives from short-term conversion toward long-term diner value, including offline evaluation and online experimentation.
• Evaluate and bring applicable information-retrieval and recommender-system research into production, including LLM-driven query and intent understanding, embedding-based retrieval, sequential user representations for cold start, and real-time inference.
• Raise engineering and operational standards across teams for model evaluation and scorecards, reproducible training pipelines, safe deployment, SLOs, observability, and technical-debt management.
• Partner with Product, Search Engineering, Ads, and Data Platform to shape roadmaps, identify risks, and ensure data and infrastructure are available when needed.
• Mentor senior and mid-level engineers, participate in hiring, and strengthen the team's technical depth.
• Translate technical trade-offs into business terms for product and executive stakeholders, and document decision rationales.
• Question existing assumptions and analyze and improve business performance.

Benefits

• Competitive compensation package with equity and a 401(k).
• Choice of medical, dental, and vision plans.
• Company-paid short- and long-term disability coverage.
• Paid time off, including flexible time off for exempt employees, paid vacation for non-exempt employees, and paid sick leave in compliance with applicable law.
• Paid parental leave.
• Discounted meals and exclusive perks across the Wonder family of brands.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior