Grafana Labs is building an Interactive Learning system, an open source, in-product learning experience that helps users learn and succeed without leaving Grafana. A central part of that vision is a personalized recommendation system that helps each user discover the next guide, action, or product experience most likely to help them succeed
Today, the Interactive Learning tool includes a rule-based recommendation engine that provides useful contextual recommendations. We are hiring an ML Engineer to lead its evolution into an increasingly personalized, continuously improving system driven by real-time product behavior, content metadata, customer context, and experimentation
This is an applied product data science role. You will personally build, deploy, and operate recommendation models, design experiments, establish evaluation methodology, and define the scientific roadmap. You will partner closely with software engineers who own the production recommender codebase and with an existing Data Analyst who supports measurement, instrumentation, and analysis across Developer Advocacy
The long-term vision is ambitious, but we do not expect it to arrive in one release. We are looking for someone who can understand the whole problem, establish strong foundations, and ship measurable improvements into the existing recommender one iteration at a time
Evolve the Interactive Learning Plugin's recommendation system
Develop increasingly personalized approaches to candidate selection, ranking, sequencing, and next-best-action recommendations
You’ll own a real-time recommendation service
Build and operate applied models
Develop, validate, version, monitor, and iterate on models used by the recommendation system
You’ll own model training & serving
Define what recommendation quality means
Develop offline, online, and longitudinal measures of recommendation performance
You’ll own feature pipelines, monitoring of the model and architecture
Ship incremental improvements
Use the data and infrastructure available today while identifying the instrumentation and platform capabilities needed tomorrow
Integrate improvements into the existing recommender rather than waiting for a complete replacement system
Partner across disciplines
Work closely with software engineers & data analysts to productionize models and integrate them safely into the recommender service
Partner with the Product Analytics team on metric definitions, instrumentation, data quality, dashboards, and experiment analysis
Collaborate with Developer Advocacy, Docs, Product, Engineering, GTM, and other teams to translate ambiguous needs into testable hypotheses and measurable product decisions
Explain modeling choices, tradeoffs, uncertainty, and results clearly to both technical and non-technical audiences