Data Scientist with Java Expertise (Colombia) (Medellín)

Project description The primary goal of the project is the modernization, maintenance and development of an eCommerce platform for a big US-based retail company, serving millions of omnichannel customers each week. Solutions are delivered by several Product Teams focused on different domains
- Customer, Loyalty, Search and Browse, Data Integration, Cart. Current overriding priorities are new brands onboarding, re-architecture, database migrations, migration of microservices to a unified cloud-native solution without any disruption to business. Responsibilities
- Design, develop, and optimize semantic and vector-based search solutions leveraging Lucene/Solr and modern embeddings.
- Develop scalable data pipelines and APIs for indexing, retrieval, and model inference.
- Integrate ML models and search capabilities into production systems.
- Evaluate, fine-tune, and monitor search performance metrics.
- Collaborate with software engineers, data engineers, and product teams to translate business needs into technical implementations.
- Stay current with advancements in search technologies, LLMs, and semantic retrieval frameworks. Qualifications
- 5+ years of experience in Data Science or Machine Learning Engineering, with a focus on Information Retrieval or Semantic Search.
- Strong programming experience in both Java and Python (production-level code, not just prototyping).
- Deep knowledge of Lucene, Apache Solr, or Elasticsearch (indexing, query tuning, analyzers, scoring models).
- Experience with Vector Databases, Embeddings, and Semantic Search techniques.
- Strong understanding of NLP techniques (tokenization, embeddings, transformers, etc.).
- Experience deploying and maintaining ML/search systems in production.
- Solid understanding of software engineering best practices (CI/CD, testing, version control, code review). Postúlate en Kit Empleo: kitempleo.com.co/empleo/1b48rd