Machine Learning Search Engineer, Services Special Projects

What you'll do

• Design and maintain large-scale, low-latency search systems capable of handling high-volume production traffic.
• Integrate traditional keyword search with vector-based semantic search using embedding models and vector databases.
• Develop NLP pipelines for intent classification, entity extraction, semantic parsing, and query expansion.
• Implement machine learning models such as Learning to Rank and Cross Encoder based models for multi-stage reranking.
• Build offline and online evaluation metrics and A/B testing frameworks to measure search quality.
• Deploy and optimize LLMs and embedding models directly within the production query path.
• Develop data processing pipelines and manage real-time inference using tools like Spark, Flink, and Kafka.

What we're looking for

• Bachelor's or Master's degree in Computer Science, Machine Learning, Statistics, or a related field.
• 10+ years of experience in Machine Learning, Data Science, or Software Engineering with a focus on search infrastructure and information retrieval.
• Experience building and deploying large-scale, low-latency search systems in production environments.
• Deep understanding of information retrieval, query understanding, multi-stage ranking algorithms, and deep learning architectures like transformers.
• Proficiency in Go, Java, C++, and Python, along with experience using PyTorch and XGBoost.
• Experience with vector search (FAISS), search infrastructure (OpenSearch/Elasticsearch), and data processing tools (Spark, Flink).
• Hands-on experience deploying and optimizing LLMs, embeddings, and ML models in production query paths.
• Familiarity with cloud environments (AWS), containerization (Docker, Kubernetes), and streaming platforms like Apache Kafka.