Stellenbeschreibung
Senior ML/Backend Engineer (Knowledge Graphs + RAG)
$160,000 - $180,000 + Benefits + PTO
United States - Remote
Are you an experienced ML/Backend Engineer with deep expertise in Python, knowledge graphs, and retrieval-augmented generation (RAG)? Do you want to design and scale AI-powered systems that strengthen access to reliable, verifiable information worldwide?
This is an exciting opportunity to join an organisation with a positive social impact, whilst benefiting from a remote-first culture and an excellent benefits package.
My client mission-driven non-profit building open-source tools that support journalists, fact-checkers, and global communities. The team develops critical digital infrastructure that helps people access trusted knowledge in fast-changing, complex information environments.
In this role, you'll take ownership of mission-critical systems at the intersection of machine learning, backend engineering, and applied research. You'll architect pipelines, scale services, and integrate cutting-edge AI strategies into production to deliver trusted, scalable, and cost-efficient knowledge workflows.
This is a hands-on, high-impact role perfect for engineers who thrive at the intersection of ML and backend development, bridging research with production in service of a global mission.
The Role
Architect ingestion pipelines to transform raw documents into structured Neo4j knowledge graphs and build/refine Python/FastAPI services for ingestion and Q&A.
Lead experimentation on RAG approaches and develop evaluation frameworks for rigorous testing and analysis.
Optimize retrieval and answering workflows for performance, cost, and reliability while handling conflicting or time-sensitive data.
Collaborate with researchers and engineers to integrate experimental approaches into production and ensure code quality, observability, and documentation.
Scale systems from prototypes to production-ready services.
The Person
8+ years in software engineering or applied ML, including leadership experience, with expertise in Python, backend systems, and ML-powered applications.
Strong skills in systems design, architecture, and building data-intensive APIs, with a track record of productionizing ML prototypes into scalable services.
Background in RAG, LLMs, or knowledge graphs, including designing and evaluating experiments.
Familiarity with CI/CD, cloud infrastructure, and observability, with excellent collaboration and communication skills bridging research and engineering.
