Build real-time conversational intelligence at Apple in a role focused on conversational AI Services Special Projects. You will help deliver low-latency LLM experiences by owning the conversational intelligence layer, including agent reasoning and tool-calling, knowledge services that keep answers accurate and grounded, and evaluation practices that integrate into the development workflow. This is an onsite role in Cupertino, CA, with a salary range of USD 184,700 to 324,800 per year.
What you’ll do
- Design multi-turn conversational experiences that support real dialogue, not one-off prompts.
- Build agent logic that plans and calls tools to complete user requests.
- Develop query understanding models that convert natural language into structured intent.
- Optimize both large and small models for real-time performance while keeping cost in check.
- Contribute to response quality by helping ensure every answer is accurate and grounded.
- Build and scale knowledge graph services that resolve, enrich, and expand requests with low latency.
- Connect the system to real-time data sources so responses remain current.
- Create automated multi-turn evaluation workflows, including LLM-as-judge, integrated directly into development.
Required experience
- Master’s degree in Computer Science, Machine Learning, NLP, or a related field.
- 7+ years of experience as a software or machine learning engineer, with significant focus on conversational AI, search, or LLM-powered systems.
- Strong programming skills in Go and Python, plus at least one of Java or Scala.
- Hands-on experience shipping conversational AI or dialogue systems, including intent and slot understanding, multi-turn context management, clarification, and disambiguation.
- Production experience with LLM-powered applications: prompt design, tool/function calling, structured output generation, and agent orchestration patterns.
- Demonstrated LLM inference optimization experience, including distillation, quantization, batching, KV-cache tuning, caching, and profiling to identify bottlenecks.
- Experience deploying and serving LLMs or ML models on the production request path using serving frameworks such as vLLM, SGLang, Triton, or TorchServe.
- Experience with knowledge graphs and low-latency lookup or retrieval services.
- Fluency with PyTorch and the Hugging Face ecosystem (transformers, PEFT).
- Familiarity with cloud environments (including AWS) and containerization (Docker, Kubernetes).
- Excellent communication skills and a collaborative mindset.
Technology focus
Go, Python, Java, Scala, PyTorch, Hugging Face, transformers, PEFT, vLLM, SGLang, Triton, TorchServe, AWS, Docker, Kubernetes, KV-cache tuning, Cassandra, Redis, SSTables, TigerGraph, Neo4j, LoRA, adapters, MLflow, Weights & Biases, DVC.
Benefits
- Comprehensive medical and dental coverage.
- Retirement benefits.
- Discounted products and free services.
- Reimbursement for certain educational expenses, including tuition.
- Potential for discretionary bonuses or commission payments, and relocation eligibility.
- Participation in Apple’s discretionary employee stock programs may make you an Apple shareholder.
- Eligible for discretionary restricted stock unit awards.
- Ability to purchase Apple stock at a discount through the Employee Stock Purchase Plan.
Preferred qualifications
- Ph.D. in Computer Science, Machine Learning, NLP, or a related field.
- Experience fine-tuning and distilling LLMs for task-specific use, including query parsing, classification, and response generation (for example, LoRA/adapters and teacher/student setups).
- Experience designing knowledge graph schemas, building graph compilation and ingestion pipelines, and working with graph databases such as TigerGraph or Neo4j.
- Deep experience with KV stores and in-memory serving for low-latency lookups (for example, Cassandra, Redis, SSTables).
- Experience calibrating LLM judges against human judgments for multi-turn conversations, including inter-annotator agreement and judge reliability tracking.
- Experience with personalization and memory in conversational systems, applying privacy principles such as data minimization and on-device processing.
- Experience implementing safety guardrails for LLM-powered agents, including prompt-injection defenses and adversarial evaluation.
- Familiarity with experiment tracking and data/model versioning tools (MLflow, Weights & Biases, DVC).
- Deep understanding of distributed systems and service design, including architecting and leading projects with cross-functional stakeholders.
- Published work or patents in conversational AI, information retrieval, knowledge graphs, or efficient inference.