We are seeking a highly experienced ML Engineer to build, deploy, optimize and operationalize Small and Large Language Model (LLM)-based applications, with a strong emphasis on MLOps/LLMOps and scalable production systems.
Description
As an AI Engineer on our team, you will own the infrastructure and tooling that let LLM-powered features ship reliably at Apple scale: the CI/CD pipelines and serving infrastructure that get a model into production, and the observability, versioning, and governance that keep it trustworthy once it's there. You'll work across the full model lifecycle, from experimentation and fine-tuning through deployment, monitoring, and retirement.
That ownership extends to the data feeding these systems and the infrastructure serving them. You'll build pipelines that ingest and enrich multimodal data through feature stores and lineage-tracked storage, deploy and operate services on cloud-native infrastructure such as Kubernetes, and expose them through well-modeled APIs. You'll also optimize models for production through quantization, distillation, and compilation, and implement the governance workflows, approval gates, and audit trails that keep every model compliant on its way into production.
You'll also own the trust side of the system: building the safety guardrails that keep model outputs safe from misuse and treating user privacy as a design constraint rather than an afterthought. As a senior member of the team, you'll mentor other engineers and help set the technical standards the rest of the team builds against.
This is a role for someone who's comfortable operating at the intersection of ML and distributed systems, as much at home tuning GPU utilization and KV-cache for low-latency inference as designing the versioning strategy that makes a rollback safe.
Minimum Qualifications
Master's degree in Computer Science, Engineering, or a related field
8+ years of experience in Machine learning and software engineering
Proven track record of shipping production-grade ML/LLM systems
Strong understanding of LLMs, fine-tuning, prompt engineering, and RAG patterns
Experience building pipelines that process multimodal data (structured and image) and integrate ML model inference, including LLMs and embedding models, for data enrichment and transformation
Hands-on experience deploying, serving, and optimizing LLMs or ML models in production, including inference runtimes/compilers (ONNX Runtime, TensorRT/TensorRT-LLM), serving frameworks (Triton, vLLM, SGLang, TorchServe, or similar), and tuning batching, KV-cache, and GPU utilization for low-latency, high-throughput inference
Experience with vector search technologies (e.g., Pinecone, Milvus) and storing/serving embeddings (e.g., pgvector, FAISS)
Experience with feature stores (e.g., Feast) and data lineage tracking
Strong proficiency in Python, with solid software engineering fundamentals, including backend service frameworks (e.g., Flask, FastAPI), for building ML/LLM services, pipelines, and tooling
Working proficiency in Java or Scala, sufficient to integrate with JVM-based data infrastructure (e.g., Spark, Flink, Kafka clients) and the broader services platform.
Experience with distributed systems, cloud platforms (e.g., AWS), container orchestration (Kubernetes), CI/CD pipelines, and building Data Pipelines on Spark using Airflow
Experience with ML lifecycle management and versioning practices, including experiment tracking, model registry, deployment automation, and dataset/model versioning tools (e.g., DVC, MLflow, Weights & Biases, Delta Lake)
Experience with workflow orchestration platforms (Airflow)
Excellent communication skills and a collaborative, team-oriented mindset
Preferred Qualifications
Ph.D. in Computer Science, Machine Learning, or a related field
Experience with Go
Solid understanding of machine learning algorithms, model evaluation metrics, and data processing pipelines
Active participation in open-source projects related to AI/ML or backend development
Familiarity with graph databases such as TigerGraph
Experience defining SLAs, quality metrics, and observability standards for large-scale data platforms, with hands-on use of monitoring/alerting tooling (e.g., Prometheus/Grafana, Datadog, or OpenTelemetry-based tracing).
Track record of mentoring engineers and influencing technical direction across a team or organization
Working knowledge of data privacy principles and practices (e.g., data minimization, access controls, privacy-preserving measurement) and experience applying them to ML data pipelines
Experience implementing model governance frameworks, including approval workflows, audit trails, and compliance controls
Experience implementing safety guardrails for LLM-powered systems, including content moderation, prompt-injection defenses, and red-teaming or adversarial evaluation practices
Hands-on experience with observability and evaluation tools for LLMs (e.g., LangSmith, Weights & Biases, MLflow)
