We are seeking ML Search Engineers who enjoy building a modern, machine-learning–driven search platform that powers product discovery across e-commerce ecosystem. As an ML Search Engineer, you’ll work hands-on implementing and supporting the machine learning pipelines that drive intelligent search, relevance, and intent understanding.
This role sits at the core of a newly formed Search Engineering team and works closely with a senior ML Architect and the Innovation organization. You’ll help take an existing ML search proof-of-concept and evolve it into a scalable, production-ready system used across dot-com and internal branch platforms.
This is a hands-on engineering role focused on building, operating, and improving ML systems in production—not research-only work.
Responsibilities:
- Implement ML-driven search components designed by the Search Architect
- Build and maintain Python-based ML pipelines for embeddings, inference, and relevance
- Work with vector search and similarity matching to support intent-based product discovery
- Support GPU-based workloads for model computation and inference
- Participate in MLOps workflows, including deployment, monitoring, retraining, and maintenance
- Help rerun and refresh embeddings as product data evolves over time
- Collaborate with Innovation, Architecture, and Engineering teams to produce ML systems
- Debug, optimize, and improve performance, reliability, and relevance of search pipelines
- Contribute to ongoing improvements as the search platform evolves
Required Qualifications:
- Strong Python development experience (primary language)
- Experience building or supporting machine learning pipelines in production
- Understanding of ML lifecycle concepts (training, inference, retraining, monitoring)
- Familiarity with MLOps principles
- Experience working with large datasets and model outputs
- Ability to work hands-on with evolving systems and ambiguous requirements
- Strong problem-solving and collaboration skills
Preferred Qualifications:
- Experience with vector databases or similarity search
- Exposure to embeddings, semantic search, or recommendation systems
- Experience with GPU-based workloads
- Cloud ML experience (GCP, AWS, or Azure)
- Prior work on e-commerce search, discovery, or relevance systems
