About this role
Summary: Design and build production RAG pipelines, multi-agent AI systems, and LLM-powered tools for enterprise clients in energy, tech, and finance sectors. Requires strong Python skills and experience with frameworks like LangChain or AutoGen.
GenAI Engineer — LLM & Agentic Systems
Can you build a GenAI system that goes to production — not just a demo that impresses in a boardroom?
About the opportunity:
Jobvous Staffing Solutions is placing Generative AI Engineers at Houston's energy, technology, and financial services companies. These companies are past the experimentation phase — they're building production RAG systems, multi-agent workflows, and LLM-powered tools that operate at enterprise scale.
This is the most in-demand AI profile in Houston right now. If you've shipped GenAI systems that real users rely on, we want to talk to you immediately.
Responsibilities:
Design and build production RAG pipelines and LLM-powered applications
Develop multi-agent AI systems using LangChain, AutoGen, or similar frameworks
Build and deploy AI copilots and decision-support tools for enterprise workflows
Integrate GenAI solutions with existing enterprise systems via APIs
Evaluate and fine-tune open-source and proprietary LLMs for domain-specific tasks
What we are looking for:
2+ years building production GenAI / LLM systems (not just prototypes)
Strong Python and prompt engineering skills
Hands-on experience with LangChain, LlamaIndex, or AutoGen
RAG architecture, vector databases (Pinecone, Weaviate, ChromaDB) experience
Azure OpenAI or AWS Bedrock experience highly valued
GitHub with live GenAI projects is a major differentiator — include your link