Machine Learning Ops, Applied Machine Learning Full-time

Summary
Apple’s Applied Machine Learning team has built systems for a number of large-scale data science applications. We work on many high-impact projects that serve various Apple lines of business. We use the latest in open source technology and as committers on some of these projects, we are pushing the envelope. Working with multiple lines of business we manage many streams of Apple-scale data. We bring it all together and unleash business value. We do all this with an exceptional group of software engineers, data scientists, DevOps engineers and managers. We are looking for a talented and dedicated engineers to join our team to bring passion for infrastructure and distributed systems, to build world-class platforms/products at a very large scale across cloud environments.

Key Qualifications
4+ years of experience in Python Programming

Extensive experience in deploying and managing the applications on AWS/GCP & Kubernetes

Deep understanding on RAG based pipelines for Model inferencing, GuardRails

Experience in open source LLM App frameworks like LangChain/LlamaIndex

Exposure to Cloud managed services like AWS BedRock/GCP Vertex AI

Good Understanding of Agents in GenAI

Strong Experience in Infrastructure templating tools like CloudFormation, Terraform

Experience in GitOps based deployment tools like Spinnaker/Flux/ArgoCD

Strong proficiency with Helm and Kustomize for managing Kubernetes applications and configurations.

Experience in managing Embeddings using Vector databases

Exposure to Promot engineering

Experience in observability & traceability for Large Language Models.

Experience in Performance tuning on operating systems like Linux

Excellent analytical & problem solving skills

Description
Join Apple’s Applied Machine Learning Team, as a Senior Software Engineer, to enable GenAI across our Applications & Platforms. Candidates should have strong background in LLM core concepts, be proficient in setting up and supporting the large scale big data applications in public cloud like AWS/GCP.

The main responsibilities for this position include:

Build LLM Applications using open source LLM App Frameworks, AWS BedRock/GCP Vertex AI

Evaluate and port Language Models onto optimized infrastructure to reduce cost and increase performance

Build tools to benchmark and compare various embedding databases, LLMs

Build & Support CI/CD tools to port & manage applications on AWS/GCP & Kubernetes

Build automation to enable self-healing systems

Ability to troubleshoot application specific, core network, system & performance issues.

Build a multi-tenancy system by enforcing data protection between different use cases.

Involvement in challenging and fast paced projects supporting Apple’s business by delivering innovative solutions.

The candidate is expected to be self-motivated, proactive, and a solution-oriented individual.

Education & Experience
BS in computer science with 4+ years or MS plus 2+ years experience or related experience.

Additional Requirements

• Exposure to various LLM infrastructure like GPUs, TPUs & Inferentia is preferred
• Exposure to LLM runtime like Triton, Frameworks like TensorRT, vLLM is an added advantage.
• Exposure to general Java troubleshooting skills