Senior AI Platform Engineer: Build Internal AI Apps

PCOnline; Newark (DE); On-site; USD 120,000 - 160,000; Full time

Job summary

PCOnline, based in Newark, Delaware, seeks aSenior AI Platform Engineer to build and operate internal AI capabilities and the AI application portal. You will own reusable components for model access, agent execution, and system integration, leveraging APIs and cloud services.

You will collaborate with AI, software, data, and IT teams to deploy LLM applications, RAG solutions, and agent workflows, while ensuring security, monitoring, and cost controls across the platform.

Qualifications

• Two or more years of software development, systems integration, or automation experience.
• Practical Python programming and API usage for connecting apps or automating workflows.
• Hands-on experience building LLM apps, RAG solutions, or agent workflows.
• Familiarity with Git, basic database concepts, and software testing and debugging.
• Ability to translate business needs into practical technical solutions and manage tasks.

Responsibilities

• Design, build, and maintain the internal AI application portal and reusable capabilities for model access, agent execution, and system integration.
• Develop and deploy LLM applications, RAG solutions, and agent workflows connecting to company data sources and APIs.
• Translate business requirements into practical technical solutions and coordinate with teams on scope and trade-offs.
• Implement access controls, data protection, audit logging, and approval mechanisms for AI apps with IT collaboration.
• Establish evaluation, testing, monitoring, and cost-tracking practices for reliable operations.
• Work with business owners to assess adoption and validate improvements in efficiency, quality, cost, or capacity.

Skills

Python

APIs

LLM apps

RAG solutions

Git

Software testing

Troubleshooting

Cloud services

SQL basics

Tools

AWS

Amazon Bedrock

Job description

PCOnline, based in Newark, Delaware, seeks aSenior AI Platform Engineer to build and operate internal AI capabilities and the AI application portal. You will own reusable components for model access, agent execution, and system integration, leveraging APIs and cloud services.

You will collaborate with AI, software, data, and IT teams to deploy LLM applications, RAG solutions, and agent workflows, while ensuring security, monitoring, and cost controls across the platform.