Staff Machine Learning Engineer, Recommendations
About this role
The Staff Machine Learning Engineer, Recommendations, works to serve as a technical anchor for the machine learning and AI capabilities at ZipRecruiter. This individual will be instrumental in shaping the multi-year ML roadmap for core components of the marketplace, such as recommendation engines and matching algorithms. The day-to-day work involves translating complex machine learning research into robust, low-latency production systems that handle high-throughput data interactions. A significant part of the role involves architecting state-of-the-art ML systems responsible for dynamic interaction prediction and candidate ranking within a complex two-sided marketplace environment.
This role exists to solve intricate matching and recommendation challenges inherent to connecting job seekers and employers in real time. The engineer will also take on an organizational leadership function, mentoring other Machine Learning Engineers and establishing standards for how models are developed, deployed, and evaluated at scale across the company. It requires a strong ability to balance deep algorithmic contributions with strategic technical guidance.
Candidates who thrive in environments requiring both deep technical execution and cross-functional technical leadership would perform well in this position. This role is ideal for someone who enjoys driving foundational architectural decisions while also focusing on production excellence and team mentorship.
What you will do
- Drive the overall Machine Learning strategy and roadmap in collaboration with Engineering and Product Leadership.
- Design and own the architecture for high-scale ML systems managing dynamic interaction prediction and candidate retrieval.
- Optimize the dynamics of the two-sided marketplace by tackling complex matching problems like real-time intent prediction and cold-start issues.
- Provide technical leadership by mentoring other Machine Learning Engineers and Data Scientists across various teams.
- Ensure end-to-end model ownership, encompassing feature engineering, distributed training, and rigorous offline/online evaluation through A/B testing.
- Focus on optimizing systems for real-time latency to ensure high performance in production environments.
What you need
- Possess over eight years of professional experience developing and deploying machine learning models within large-scale production settings.
- Must have a proven history of architecting and shipping complete ML solutions that successfully serve production traffic at scale.
- Requires deep domain expertise in areas such as Recommendation Systems, Personalization, Ranking & Retrieval, or Interaction Prediction.
- Demonstrate strong software engineering fundamentals backed by practical expertise in modern deep learning frameworks like PyTorch and TensorFlow.
- Should have proven experience in technical leadership, effectively driving technical alignment across diverse engineering and product teams.
- A strong background in statistical modeling, designing online experimentation methodologies, and creating offline metrics is necessary.
Nice to have
- Experience in Two-Sided Marketplaces
- Experience with Two-Tower Neural Networks
- Experience with Graph Neural Networks (GNNs)
- Experience with Transformer-based retrieval models
- Experience with Contextual Bandits
Benefits
- Competitive compensation
- Exceptional benefits package
- Flexible Vacation & Paid Time Off
- Employer-matched 401(k) plan
- Equity
- Bonuses
- Commission
Skills and tech stack
Questions candidates ask
What is the remote policy?
Most US-based positions can also be performed remotely; exceptions will be noted in the Minimum Qualifications.
What is the salary range for this role?
The US base salary range for this full-time position is $205,000.00-$265,000.00 USD.
What is the required tech stack?
The role requires hands-on expertise using modern deep learning frameworks, specifically PyTorch and TensorFlow.
What is the team structure like?
The role reports directly to the Director of Recommendation Systems, and the position has org-wide reach.