AI Engineer (LLM / Agentic Workflows) — Quantum SaaS
Posted
Summary
Mid-level AI engineer at Quantum Elements builds LLM-driven agents and RAG pipelines that translate natural-language requests into quantum simulation, optimization, and orchestration workflows on an AI-native quantum computing SaaS platform, deploying on AWS with a focus on latency, cost, and reliability.
About the Role
We are building an AI-native platform for quantum computing, where users interact with complex systems through agentic AI workflows and natural language interfaces.
We’re looking for a mid-level AI Engineer to join our team and help design and implement LLM-driven agents that translate user intent into structured computational workflows, including simulation, optimization, and orchestration of quantum tasks.
This is a hands-on individual contributor role focused on building real production systems at the intersection of LLMs, reasoning agents, and scientific computing.
What You’ll Do
- Design and implement agentic AI workflows
- Build and maintain RAG pipelines
- Develop LLM-powered orchestration layers
- Implement evaluation and observability for LLM systems
- Deploy and operate systems on AWS
- Optimize latency, cost, and reliability
What We’re Looking For
- 2–5 years experience in AI/ML/software
- Strong Python skills
- Experience with LLMs and RAG
- Experience with agentic frameworks
- Production deployment experience
Nice to Have
- Multi-agent systems
- Scientific domain exposure
- Workflow orchestration
Why This Role is Interesting
- Build real AI systems
- Work on agentic workflows
- Intersection of LLMs and scientific computing
What Success Looks Like
- End-to-end task execution from user input
- Reliable multi-step agents
- Production scalability
To apply, include:
A GitHub repo or project involving LLMs / agents
A short explanation (3–5 sentences) of a system you built
Your approach to debugging LLM systems