Staff Software Engineer – Platform and Infrastructure
| Company | Snap |
|---|---|
| Location | Palo Alto, CA, USA, Seattle, WA, USA |
| Salary | $195000 – $343000 |
| Type | Full-Time |
| Degrees | Bachelor’s |
| Experience Level | Expert or higher |
Requirements
- Bachelor’s degree in a technical field such as computer science or equivalent experience
- 9+ years industry software engineering experience
- Experience with large scale distributed systems, and Cloud Computing
- Hands-on knowledge of cloud infrastructure and operational excellence patterns and practices
- Background with building high availability and mission critical distributed systems
- Experience with Java, Go, C++, and/or Python
- Ability leading and executing large, complex technical initiatives
- Ability to proactively learn new concepts and apply them at work
Responsibilities
- Design, implement, and optimize infrastructure powering large-scale retrieval and ranking systems, focusing on vector, inverted index, graph retrieval, and real-time data ingestion.
- Develop and enhance ranking and retrieval algorithms for recommendation engines, ensuring efficient and relevant results.
- Lead technical strategy for large-scale retrieval and ranking pipelines, setting roadmaps, creating measurable goals, and driving execution across teams.
- Collaborate with cross-functional teams, including Product, Operations, and Cloud Providers, to develop scalable and efficient infrastructure solutions.
- Evaluate trade-offs between latency, accuracy, and scalability in search and recommendation models, mentoring teams on best practices
Preferred Qualifications
- Experience developing and fine-tuning ranking and retrieval infrastructure / algorithms for large-scale recommendation systems.
- Deep understanding of recommendation models, user behavior modeling, and multi-objective optimization in recommendations.
- Hands-on experience with learning-to-rank (LTR) models, reinforcement learning for ranking, and contextual bandits.
- Experience with feature engineering, embedding-based retrieval, and neural search techniques.