AI - Integration Application Architect

TekWissen • Phoenix, AZ

2d • Hybrid

About The Position

Design how AI models integrate with core systems and applications. Integrate large language models (LLMs) and AI frameworks, build retrieval-augmented generation (RAG) pipelines, and use vector databases where needed. Set up APIs and microservices to connect AI capabilities to the broader technology stack. Evaluate AI platforms for cost, performance, and compliance, and handle data privacy, model risk, and production monitoring. Work closely with data science, engineering, and infrastructure teams. This is a six-month temporary assignment in Phoenix, Arizona, with work listed as onsite / hybrid and a day shift.

Requirements

• 8+ years in application or solution architecture.
• 3+ years in AI/ML integration.
• Hands-on experience with LangChain, Hugging Face, TensorFlow, or similar technologies.
• Experience with LLM platforms such as OpenAI, Anthropic, Azure OpenAI, or AWS Bedrock.
• Strong understanding of RAG and vector databases such as Pinecone, Weaviate, or FAISS.
• Strong background in APIs, microservices, and event-driven architecture.
• Comfortable working in AWS.
• Strong coding skills in Python and Java.
• Understanding of MLOps/LLMOps.

Responsibilities

• Design integration of AI models with core systems and applications.
• Integrate LLMs and AI frameworks using tools such as LangChain or Semantic Kernel.
• Build RAG pipelines and work with vector databases where needed.
• Set up APIs and microservices to connect AI to the broader technology stack.
• Evaluate AI platforms for cost, performance, and compliance fit.
• Address data privacy, model risk, and monitoring for production systems.
• Collaborate with data science, engineering, and infrastructure teams.

What This Job Offers

• Career Level: Senior
• Education Level: No Education Listed