Machine Learning Engineer - Search & Retrieval Systems
United StatesFull-TimeMiddle
Salary225000 - 280000 USD per year
Apply NowOpens the employer's application page
Job Details
- Experience
- 5–8+ years
- Required Skills
- PythonElasticSearchA/B testingLLM
Requirements
- 5–8+ years of experience in search, ranking, or retrieval systems in production environments
- Strong expertise in Elasticsearch or similar technologies (OpenSearch, Solr, Vespa), including indexing and query design
- Hands-on experience with learning-to-rank approaches such as LambdaMART, LightGBM, or XGBoost
- Strong Python engineering skills with production-grade software development practices
- Experience with dense retrieval, embeddings, and vector search (ANN systems, semantic retrieval)
- Solid understanding of ML evaluation methodologies (nDCG, MRR, A/B testing, offline/online metrics)
- Experience building end-to-end ML pipelines from training data to deployment and monitoring
- Ability to work with behavioral data and translate signals into ranking improvements
- Strong problem-solving skills with a focus on measurable product impact
- Excellent communication skills and ability to collaborate across engineering and product teams
Responsibilities
- Own and evolve hybrid search systems, including lexical search, vector retrieval, and multi-stage ranking pipelines
- Design and deploy learning-to-rank models (e.g., LightGBM, XGBoost, LambdaMART) for production search ranking
- Build adaptive retrieval systems that dynamically adjust search behavior based on query intent, context, and category
- Develop and maintain Elasticsearch-based infrastructure, including index design, query optimization, and hybrid retrieval strategies
- Build feedback loops using behavioral signals (CTR, conversions, engagement) to improve ranking and retrieval quality
- Design offline and online evaluation frameworks, including A/B testing and ranking metric analysis (nDCG, MRR, precision/recall)
- Own product enrichment pipelines, including LLM-based metadata generation and large-scale indexing workflows
- Integrate query understanding outputs (intent, attributes, constraints) into retrieval and ranking logic
- Build scalable business logic layers for product ordering, including separation of organic and sponsored results
- Instrument and monitor search performance, ensuring regression detection and continuous system improvement
View Full Description & ApplyYou'll be redirected to the employer's site
