Staff Software Engineer, Cloud Infrastructure

Job Description

Design, build, and operate secure, scalable AWS infrastructure and production LLM systems, including model endpoints, RAG pipelines, vector search, data ingestion, and IoT deployments. Improve reliability, performance, safety, and cost through evaluation, observability, security controls, and close collaboration with product and engineering teams.

Requirements: Candidates should have strong AWS infrastructure experience, hands-on experience shipping or operating production LLM applications, and familiarity with RAG, orchestration frameworks, and Python data pipelines. The role also calls for end-to-end ownership, security-minded engineering, quantitative evaluation, and clear communication; 9+ years of AWS serverless or container experience is listed as a bonus.

Key Skills: AWS Cloud Infrastructure, Infrastructure as Code, LLM Platform Engineering, Retrieval-Augmented Generation, Python Data Pipelines, AWS Bedrock, Amazon SageMaker, LangChain, Vector Search, CI/CD, Cloud Security, AWS IoT, Observability, Machine Learning Infrastructure, Data Engineering, Incident Response

Benefits: Health Insurance, Paid Time Off, Paid Company Holidays, 401(k)