Machine Learning Engineer – Search & Retrieval Systems

Accountabilities:

In this role, you will own the end-to-end search and retrieval systems, ensuring continuous improvement in relevance, ranking quality, and system adaptability. You will work across ML modeling, search infrastructure, and data-driven experimentation to improve product discovery performance at scale.

• 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

Requirements:

The ideal candidate has strong experience in search systems, applied machine learning, and production-scale retrieval engineering. You are pragmatic, highly analytical, and comfortable building systems that combine ML models with real-time search infrastructure.

• 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

Benefits:

• Competitive compensation ($225,000 – $280,000 USD depending on experience and location)

• Equity in the form of stock options

• Comprehensive medical, dental, and vision insurance

• 401(k) retirement plan

• Fully remote work across the United States

• Flexible PTO and company holidays

• Periodic offsites and team gatherings

• Opportunity to work on cutting-edge AI search and retrieval systems at large scale

How Jobgether works:
We use an AI-powered matching process to ensure your application is reviewed quickly, objectively, and fairly against the role's core requirements. Our system identifies the top-fitting candidates, and this shortlist is then shared directly with the hiring company. The final decision and next steps (interviews, assessments) are managed by their internal team.
We appreciate your interest and wish you the best!
 Why Apply Through Jobgether?

Data Privacy Notice: By submitting your application, you acknowledge that Jobgether will process your personal data to evaluate your candidacy and share relevant information with the hiring employer. This processing is based on legitimate interest and pre-contractual measures under applicable data protection laws (including GDPR). You may exercise your rights (access, rectification, erasure, objection) at any time.

#LI-CL1