C
Software Engineer, Data Pipelines and Search Systems
Not specifiedFull-timeData EngineeringEnterprise SoftwareData Infrastructure
Join an AI software company building an enterprise context platform for agents and developers. Own high-throughput indexing, real-time data pipelines, graph traversal, hybrid retrieval, and low-latency query systems.
Responsibilities
- Design and scale real-time data pipelines, live ETL processes, and indexing engines.
- Unify data from multiple customer integrations into a real-time knowledge graph.
- Build graph-traversal systems for enterprise artifacts.
- Optimize hybrid retrieval using lexical search, dense embeddings, graph expansion, and reranking.
- Develop offline and online evaluation frameworks for retrieval accuracy, latency, and agent task success.
- Own systems end to end, including schema design, implementation, deployment, observability, and production reliability.
- Contribute to architectural decisions involving agent coordination, context caching, and evolving agent protocols.
Requirements
- 3–5 years of experience building high-performance backend systems, distributed data pipelines, or data-intensive applications.
- Practical experience with embeddings, vector search, lexical search such as BM25, Lucene, or OpenSearch, and reranking.
- Hands-on experience using AI coding agents in an AI-native development workflow.
- Ability to take ambiguous technical problems from concept through production with substantial ownership.
Nice to have
- Experience with graph databases such as Neo4j, Memgraph, or FalkorDB.
- Familiarity with the Model Context Protocol or agentic execution frameworks.
- Background in search relevance, learning-to-rank, or synthetic evaluation generation.
- Experience in an early-stage startup.
- Bachelor’s degree in Computer Science or equivalent hands-on experience.