BenchSci

Software Engineer, Data – Query Intelligence & Infrastructure

BenchSci

contract

Posted on:

Origin:  • 🇬🇧 United Kingdom

Visit company website
✨ AI Apply
Manual Apply

Job Level

Mid-LevelSenior

Tech Stack

CloudDockerETLGoogle Cloud PlatformNeo4jPythonSQL

About the role

  • Design, implement, and own the Model Context Protocol to provide stateful information for GenAI systems.
  • Build and leverage knowledge graphs to model complex data relationships and enhance query understanding.
  • Develop and maintain robust data pipelines that populate graph databases and support efficient, real-time query analysis.
  • Develop and refine APIs providing fast, reliable access to processed data and insights from graphs and ML models.
  • Establish, monitor, and improve query performance benchmarks against large-scale graph and tabular datasets.
  • Contribute to query interpretation and NLP-driven analysis, applying ML techniques to improve system intelligence.
  • Design and implement scalable, testable solutions using modern frameworks and tools.
  • Collaborate with colleagues on the design and delivery of data-intensive ML systems that are graph and context aware.
  • Share knowledge and learn from others to continuously raise the technical bar.

Requirements

  • PhD or advanced degree in Computer Science, Software Engineering, or a related field.
  • A strong background in machine learning, NLP, query analysis, and data science applications.
  • Experience with graph technologies, including graph databases (e.g., Neo4j, Neptune) and/or graph processing frameworks (e.g., NetworkX).
  • Experience designing or working with systems that manage state or context for GenAI models; direct experience with a Model Context Protocol is a significant plus.
  • Hands-on experience in Python
  • Proficiency in query languages (e.g., SQL, Cypher, Gremlin) and optimizing queries over large, complex datasets.
  • Experience building or supporting ETL pipelines, APIs, or real-time/batch query systems.
  • Familiarity with cloud environments (GCP preferred), CI/CD pipelines, Docker, and GitHub Actions.
  • A strong understanding of performance optimization.
  • The ability to clearly communicate technical concepts to both technical and non-technical audiences.
  • A collaborative mindset and a growth mindset, staying up to date with advances in ML, graph systems, and data engineering.