About the team + role
The Agentic team at Robinhood builds and ships production AI agents that power the next generation of AI financial products. Our mission is to rapidly build, evaluate, and deploy high-performance AI agents on production-grade infrastructure, strong evaluation and observability baked in, and continuous optimization support. This role is based in our Menlo Park, CA or Bellevue, WA office(s), with in-person attendance expected at least 3 days per week.
What you'll do
As a Machine Learning Engineer on our team, your primary focus will be on the implementation and evaluation of machine learning algorithms through rigorous experimentation and testing methodologies. Your responsibilities will include:
- AI and ML Research: Evaluate cutting technologies, including but not limited to, transformer based model architecture and large foundational models to identify solutions for Robinhood specific problems.
- Model Development and Implementation: Develop and implement scalable machine learning models focusing on advanced ranking and recommendation systems, including expertise in Collaborative Filtering, Content-Based Filtering, and Hybrid models, alongside proficiency in Learning to Rank (LTR) techniques for effective prioritization. Additionally, design reinforcement learning algorithms and apply multi-armed bandit strategies to optimize decision-making in dynamic environments, balancing exploration and exploitation.
- A/B Testing and Experimentation: Design and conduct A/B tests to assess the performance of different machine learning models. This includes setting up the test environment, monitoring performance, and analyzing results.
- Data Analysis and Insight Generation: Analyze experimental data to extract actionable insights. Use statistical techniques to validate the findings and ensure their relevance and accuracy.
- Cross-Functional Collaboration: Work closely with other engineering teams, data scientists, and the marketing team to integrate machine learning models into the product and ensure they meet business requirements. Present results to different stakeholders.
- Tooling and Documentation: Build reusable libraries for common machine learning practices. Offer support and guidance to the usage of these tools. Maintain comprehensive documentation of libraries, models, experiments, and findings.
What you bring
- 5+ years of applied ML experience productionizing ML models with 2+ years focused on recommendations, ranking or personalization projects.
- A fervent interest in exploring and applying AI and ML technologies.
- Strive to solve sophisticated engineering problems that drive business objectives.
- Solid technical foundation enabling active contribution to the design and execution of projects and ideas.
- Familiarity with architectural frameworks of large, distributed, and high-scale ML applications.
- Hands-on experience in classical ML techniques with tabular data as well as modern techniques with sequential data
- Proven experience in ML with a focus on ranking, recommendation systems, multi-objective optimization, and reinforcement learning.
- Proficiency in Python, SQL, XGboost, PyTorch/TensorFlow.
- Experience with Spark, Kafka, and Kubernetes is also desirable.
- Ideally you have experience in the Finance sector.