4 days ago
Responsibilities
- Design, develop, and optimize large-scale search systems for real-time production use.
- Build search capabilities involving information retrieval, query understanding, query augmentation, and multi-stage ranking.
- Deploy, serve, tune, and optimize LLMs, embeddings, and machine learning models in production query and request paths.
- Develop systems for multi-objective optimization across relevance, diversity, freshness, and fairness.
- Build real-time systems, user feedback loops, and model retraining pipelines.
- Collaborate with AI/ML scientists and engineers to personalize user experiences and solve real-world search problems.
- Optimize models, including quantization, for production performance and quality.
- Tune key-value caches, batching, inference runtimes, and serving systems for low-latency, high-throughput inference.
Requirements
- Bachelor’s or Master’s degree in Computer Science, Machine Learning, Statistics, or a related field; a PhD is preferred.
- 10+ years of experience in Machine Learning, Data Science, or Software Engineering, with significant focus on search infrastructure and information retrieval.
- Hands-on experience building and deploying large-scale search systems in production.
- Deep understanding of information retrieval, query understanding, query augmentation, and multi-stage ranking algorithms.
- Strong foundation in deep learning architectures for search and retrieval, including transformers, cross-encoder models, graph neural networks, and learned sparse representations.
- Strong proficiency in Go, Java, C++, and Python.
- Experience with PyTorch and XGBoost.
- Familiarity with AWS, Docker, and Kubernetes.
- Extensive experience with data processing pipelines using Spark and Flink.
- Hands-on experience with vector search using FAISS and streaming platforms such as Apache Kafka.
- Experience with OpenSearch and/or Elasticsearch.
- Published work or patents in search systems, information retrieval, or related machine learning fields is preferred.
- Preferred experience includes TigerGraph, DVC, MLflow, Weights & Biases, SSTables, Cassandra, ONNX Runtime, TensorRT, TensorRT-LLM, vLLM, SGLang, Triton, and TorchServe.
Tech Stack
Apache CassandraApache FlinkApache KafkaApache SparkAWSC++DockerDVCElasticsearchGoJavaKubernetesMLflowPythonPyTorchXGBoost
Categories
About Apple
Apple designs and sells consumer electronics, software, and services for consumers and professionals worldwide, including iPhone, Mac, iPad, Apple Watch, and AirPods, plus platforms like iOS/macOS and services such as the App Store, iCloud, Music, and TV+. Its business combines device sales with services and subscriptions and in-house silicon design. Founded in 1976, Apple is headquartered in Cupertino, California, and trades on NASDAQ as AAPL.