Job description

We're looking for an exceptional AI Engineer who loves building things from scratch, moving quickly, and solving difficult problems with AI. We're looking for a builder. Someone who thrives in ambiguity, takes ownership, and enjoys turning ideas into production-ready systems. You'll work on cutting-edge AI applications, autonomous agents, workflow automation, and intelligent systems that have a direct impact on the business. What You'll Do • Design, build, and deploy production-grade AI agents and autonomous workflows • Develop agent architectures using modern LLM frameworks and orchestration tools • Build integrations with APIs, databases, internal tools, and external systems • Rapidly prototype new AI-driven products and iterate based on real-world feedback • Create scalable solutions leveraging large language models, retrieval systems, and automation frameworks • Optimize performance, reliability, and cost across AI applications • Own projects from concept to deployment with minimal oversight • Solve complex technical challenges in fast-moving, high-impact environments What We're Looking For Must-Haves • Proven experience personally building and deploying AI agents in production environments • Strong software engineering fundamentals and coding proficiency • Deep understanding of LLM applications, prompt engineering, agent architectures, and AI workflows • Experience integrating AI systems with APIs, databases, and external services • Demonstrated ability to independently deliver projects from idea to execution • Strong problem-solving skills and a bias toward action Preferred Experience Experience with tools and technologies such as: • LangChain • LangGraph • CrewAI • LlamaIndex • OpenAI APIs • Anthropic Claude • Vector databases (Pinecone, Weaviate, Chroma, Qdrant) • RAG architectures • Multi-agent systems • Python • TypeScript • FastAPI • Docker • Cloud platforms (AWS, Azure, or GCP)

Requirements

Must-haves

We're looking for an exceptional AI Engineer who loves building things from scratch, moving quickly, and solving difficult problems with AI.
Design, build, and deploy production-grade AI agents and autonomous workflows
Develop agent architectures using modern LLM frameworks and orchestration tools
Build integrations with APIs, databases, internal tools, and external systems
Rapidly prototype new AI-driven products and iterate based on real-world feedback
Create scalable solutions leveraging large language models, retrieval systems, and automation frameworks
Optimize performance, reliability, and cost across AI applications
Own projects from concept to deployment with minimal oversight
Solve complex technical challenges in fast-moving, high-impact environments
Proven experience personally building and deploying AI agents in production environments
Strong software engineering fundamentals and coding proficiency
Deep understanding of LLM applications, prompt engineering, agent architectures, and AI workflows
Experience integrating AI systems with APIs, databases, and external services
Demonstrated ability to independently deliver projects from idea to execution
Strong problem-solving skills and a bias toward action
Anthropic Claude
Vector databases (Pinecone, Weaviate, Chroma, Qdrant)
RAG architectures
Multi-agent systems
Cloud platforms (AWS, Azure, or GCP)

Nice-to-haves

None flagged.

Application prep

Use the role’s language and application details while tailoring your materials.

Keywords to mirror

aillmpythontypescriptdockerawsazuregcp

Platform: ukg
Effort: medium