Applied AI Tech Lead: RAG Pipelines & Kubernetes

SFE; Cupertino (CA); On-site; USD 140,000 - 200,000; Full time

Job summary

SFE in Cupertino, CA seeks a Tech Lead to architect and deliver cutting-edge AI solutions. You will lead development of RAG pipelines, embeddings, vector databases, and scalable deployment on Kubernetes and cloud environments.

You will work closely with customers to translate workflows into robust technical implementations, demos, and documentation, while ensuring quality through automated tests and compliant testing practices.

Qualifications

• Experience with LLMs and agent frameworks (LangChain, LlamaIndex) preferred.
• Strong Python skills and experience with vector databases and embeddings.
• Hands-on Kubernetes and Docker experience with scalable API deployments.

Responsibilities

• Build and optimize RAG pipelines and document-processing workflows.
• Design agentic AI systems with tool calling, orchestration, and reasoning loops.
• Develop AI services that integrate with customer backends and APIs.
• Collaborate with customers for demonstrations and technical documentation.
• Create and maintain automated tests and test procedures.

Skills

LLMs & agents

Python

Kubernetes

Tools

LangChain

LlamaIndex

Elastic

Milvus

Pinecone

Docker

Job description

SFE in Cupertino, CA seeks a Tech Lead to architect and deliver cutting-edge AI solutions. You will lead development of RAG pipelines, embeddings, vector databases, and scalable deployment on Kubernetes and cloud environments.

You will work closely with customers to translate workflows into robust technical implementations, demos, and documentation, while ensuring quality through automated tests and compliant testing practices.