Machine Learning Engineer, Ranking & Retrieval
New
J
JobgetherAI, Software
Based in United StatesFull-TimeSenior
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Experience
- 5+ years
- Required Skills
- ElasticSearchMachine LearningTypeScriptNLP
Requirements
- Bachelor’s degree in Computer Science, Machine Learning, or a related technical field.
- 5+ years of machine learning engineering experience focused on ranking, retrieval, information retrieval, or closely related areas.
- Proven experience owning the full ML lifecycle, including model training, deployment, production serving, and optimization.
- Hands-on experience training ranking models, including feature engineering, training pipelines, and offline evaluation.
- Strong experience building hybrid retrieval systems that combine lexical and vector search.
- Experience operating embedding inference at significant scale, ideally across very large document collections.
- Strong fundamentals in query understanding, including intent modeling and query expansion.
- Experience with permission-aware retrieval and multi-tenant architectures.
- Experience indexing large-scale user-generated content.
- Hands-on experience with OpenSearch or Elasticsearch, including sharding, index management, and real-time ingestion.
- Background in NLP, semantic search, or agentic retrieval.
- Experience with TypeScript in backend systems.
Responsibilities
- Own the complete machine learning lifecycle for ranking and retrieval models, including training, deployment, production serving, monitoring, and ongoing improvement.
- Build ranker features, training pipelines, and offline evaluation frameworks that enable reliable experimentation and measurable improvements in search relevance.
- Design, develop, and scale hybrid retrieval systems combining lexical and vector search, including large-scale HNSW implementations with disk offloading.
- Develop and operate embedding inference systems capable of processing billions of documents and supporting high-volume retrieval workloads.
- Improve query understanding through intent modeling, query expansion, and other techniques that help users retrieve more relevant information.
- Build permission-aware retrieval systems that respect multi-tenant boundaries and ensure users only access content they are authorized to retrieve.
- Create measurement and evaluation frameworks to assess search quality, identify weaknesses, and guide continuous ranking and retrieval improvements.
- Partner with Search Infrastructure, AI, and backend engineering teams to integrate ML-driven ranking and retrieval capabilities across the broader platform.
View Full Description & ApplyYou'll be redirected to the employer's site
