Senior Full Stack AI Engineer w/Node.js TypeScript in Des Moines
Job Description
Job Title: Senior Full Stack AI Engineer w/Node.js TypeScript
\n
Location: Des Moines, IA
\n
Work Arrangement: Onsite
\n
Employment Type: Contract
\n
Duration: 6+ months
\n
Domain: Information Technology | Enterprise Software & Generative AI
\n
Pay Rate: $58.00/hr W2 | $70.00/hr C2C
\n
Application Deadline: October 29, 2026
\n
No. of Opening: Two
\n
\n
SKILLS REQUIRED
\n
Primary (Must-Have):
\n
• Strong hands-on Node.js / TypeScript development experience
\n
• AWS Cloud Services (Amazon Bedrock, AWS CDK, API Gateway, Lambda, Fargate, S3, EventBridge, DynamoDB, PostgreSQL, CloudWatch)
\n
• Infrastructure as Code (IaC) via AWS CDK
\n
• Generative AI Engineering (RAG architecture, vector search, embeddings, prompt engineering, AI chatbots/copilots)
\n
\n
Secondary (Good to Have):
\n
• AI Safety & Guardrails (Prompt injection mitigation, output validation, hallucination controls)
\n
• CI/CD, Enterprise Automated Testing & Debugging
\n
• Modern Database Design (DynamoDB & PostgreSQL)
\n
\n
POSITION OVERVIEW
\n
The Engineering & Technology department is seeking a Senior Full Stack AI Engineer to accelerate the deployment of enterprise-grade Generative AI applications and knowledge assistants. Reporting to the Engineering Lead, the selected candidate will solve critical data retrieval and business process bottlenecks by engineering secure, scalable AWS-hosted backend APIs and RAG-based AI workflows. This position demands a high-output software builder capable of directly bridging cutting-edge LLM capabilities with production-ready enterprise systems.
\n
\n
ROLES & RESPONSIBILITIES
\n
• Architect, build, and deploy production-ready backend services and APIs using Node.js and TypeScript.
\n
• Design, deploy, and manage scalable cloud infrastructure using AWS CDK, integrating services including Amazon Bedrock, Lambda, API Gateway, Fargate, DynamoDB, and PostgreSQL.
\n
• Develop enterprise Generative AI workflows, leveraging retrieval-augmented (RAG), vector search, embeddings, chunking, and prompt engineering strategies to deliver reliable AI copilots.
\n
• Implement robust AI output validation, safety guardrails, content moderation, and controls to mitigate risks such as prompt injections and model hallucinations.
\n
• Collaborate cross-functionally with product, architecture, QA, security, and enterprise stakeholders to integrate scalable AI capabilities into core business workflows and maintain CI/CD pipelines.
\n
\n
BENEFITS
\n
Medical | Dental | Vision | 401(k)
\n
\n
EEOC Compliance:
\n
We are an equal opportunity employer, and all qualified applicants will receive consideration for employment.
\n
\n
DISCLAIMER
\n
AI Usage Policy: Pacer Group uses AI to assist in screening applications. Final hiring decisions are made by human recruiters based on qualifications and experience.