Job Title: Machine Learning Engineer – Search and Ranking Systems
Location: Remote work (Mexico specific)
Work Timings: Monday-Friday
Hours: 8-5 pm CST
Total Experience: 7+ years
Relevant Experience: 4+ years
Responsibilities:
Design and implement machine learning models for search and ranking (e.g., metadata classifiers, embedding models, and reranking algorithms).
Develop and optimize scalable pipelines for data ingestion, enrichment, and indexing.
Build and deploy embedding-based models for hybrid search systems, ensuring high performance and low latency.
Collaborate with backend teams to integrate Redis caching and semantic search solutions.
Work with external AI/ML APIs (e.g., OpenAI) to enhance system capabilities.
Monitor and fine-tune search ranking algorithms to improve relevance metrics.
Create semantic caching strategies and ensure seamless integration with the Hybrid Search DB.
Requirements:
Strong understanding of ML fundamentals, including NLP techniques, embeddings, and ranking models.
Proficiency in Python, TensorFlow, PyTorch, or similar ML frameworks.
Experience with search technologies (e.g., Elasticsearch, vector search systems).
Familiarity with AWS services (e.g., Lambda, S3) and scalable architectures.
Knowledge of data scraping and processing pipelines.
Hands-on experience integrating and optimizing external AI APIs (e.g., OpenAI).
Excellent problem-solving skills and ability to work in a microservices-based environment.