AI Engineer (Agentic AI / LLM / RAG)

Quick Facts

• Role: AI Engineer focused on Agentic AI, LLM applications, and RAG

Description

Design, develop, and implement production-ready agentic AI applications using LLM APIs and modern agentic frameworks. Build multi-step AI agents and conversational chatbots integrated with backend services, including RAG pipelines (embeddings, vector databases, semantic search), prompt optimization, and guardrails to improve quality and reduce hallucinations. Monitor, troubleshoot, and continuously improve deployed AI systems for performance, scalability, reliability, and low response latency.

Responsibilities

• Design, develop, and deploy LLM-powered AI applications using agentic frameworks

• Build intelligent AI agents and multi-step workflows for business use cases

• Implement RAG pipelines using embeddings, vector databases, and semantic search

• Integrate LLM capabilities into backend applications, APIs, and microservices

• Develop context-aware conversational AI and chatbot applications

• Design and optimize prompts; perform prompt evaluation and tune LLM behavior

• Implement guardrails and validation mechanisms to minimize hallucinations

• Optimize performance, scalability, reliability, and response latency

• Monitor, troubleshoot, and enhance production deployments

• Collaborate with product and engineering teams

Requirements

• Strong hands-on software engineering experience delivering production-grade applications

• Hands-on experience building agentic AI applications/agents or LLM-powered chatbots in production

• Hands-on experience with Google Agent Development Kit (ADK)

• Proficiency in Python (or comparable backend language)

• Experience integrating LLM APIs and working with LLMs

• Hands-on experience implementing RAG architectures

• Knowledge of embeddings, semantic search, and vector databases (e.g., Pinecone, Weaviate, FAISS)

• Experience with REST APIs, microservices, and distributed architectures

• Strong understanding of prompt engineering, prompt evaluation, and LLM behavior

• Ability to troubleshoot, optimize, and maintain AI applications in production

• Strong problem-solving and analytical skills; ability to work cross-functionally

• Comfortable in a fast-paced engineering environment

• Willingness to work in a hybrid environment in Houston, TX

Benefits

• Build and deploy real-world, production-ready LLM and agentic AI solutions

• Work on performance, reliability, and quality improvements for deployed AI systems