Software Engineer, Context Engine
San Francisco, CA • FullTime
Posted 3mo ago
About the job
Sierra is building a platform to enable companies to create better, more human customer experiences with AI. We are seeking a Software Engineer to join our full-stack data team. You will be instrumental in building systems that enhance the intelligence of our AI agents with every interaction. This role involves developing real-time pipelines, analytics products, and personalization primitives to transform customer conversations into business outcomes. You will contribute to architecting and building our core data platform for low-latency, large-scale data handling, including real-time eventing, streaming and batch ETL, and our data lakehouse. Additionally, you will develop systems for long-term agent memory, reusable Customer Data Platform (CDP) primitives, and optimization loops for personalized interactions that demonstrably improve business results.
Responsibilities
- Architect and build core data platform systems for low-latency, large-scale data handling.
- Develop real-time eventing infrastructure, streaming and batch ETL pipelines, and data lakehouse solutions.
- Own systems for interactive OLAP querying, orchestration, and experimentation to ensure data trustworthiness and usability.
- Develop systems for long-term agent memory and reusable Customer Data Platform (CDP) primitives.
- Implement optimization loops for agent personalization to demonstrably lift business outcomes.
- Build analytics dashboards, data visualization tools, or alerting and exploration systems.
- Develop full-stack features for data products, focusing on performance, API design, and user experience.
- Translate ambiguous questions into clear, intuitive interfaces for complex data.
Requirements
- 4-7+ years of hands-on development experience building and shipping production systems or products.
- Depth in designing, building, and operating large-scale data systems processing terabytes or petabytes of data.
- Experience with technologies like Spark, Flink, Trino/Presto, and data lakehouse formats like Iceberg or Hudi.
- Strong backend and distributed systems fundamentals in languages like Go, Scala, or Python.
- Understanding of storage engines, query plans, and data serialization formats.
- Experience implementing pragmatic data governance, lineage, and testing.
- Experience building cost-aware, highly operable data platforms.
- Proficiency in data modeling best practices (dimensional modeling, star/snowflake schemas, slowly changing dimensions).
- Experience optimizing analytical query patterns for OLAP systems and cloud data warehouses.
- Portfolio of shipped data products, including analytics dashboards, data visualization tools, or alerting and exploration systems.
- Skilled full-stack engineer with experience in TypeScript/React and a service layer like Go.
- Keen eye for performance, API design, and polish in user interfaces.
- Strong product sense around information architecture, handling empty states, and making complex data explainable.
- Practical experience with ML-powered product features such as personalization, recommendations, or classification systems.
- Passion for being on the frontier of AI products.
- High agency and a bias to action in a high-autonomy environment.
- Degree in Computer Science or related field, or equivalent professional experience.