Fulltime Role
Job Title: Gen AI Engineer
Location: Houston (Hybrid)
Job Summary
We are seeking a highly skilled Gen AI Engineer to design, develop, and optimize AI evaluation and automation pipelines for enterprise-scale AI and agentic systems. The ideal candidate will have hands-on experience building evaluation frameworks for AI agents, supporting RAG pipelines, and automating weekly evaluation workflows using golden datasets and dynamic evaluation techniques.
This role requires strong expertise in AI/LLM evaluation methodologies, Databricks environments, and automation frameworks. Experience with agentic workflows, LangGraph, and RAGAS is highly preferred.
Key Responsibilities
Design and implement AI evaluation pipelines for LLM-based applications and AI agents.
Develop automated evaluation workflows using golden datasets, benchmark testing, and dynamic evaluation methods.
Build and maintain weekly evaluation jobs for AI agents and generative AI systems.
Support and optimize RAG (Retrieval-Augmented Generation) pipelines for enterprise AI applications.
Create scalable automation pipelines within Databricks environments.
Develop evaluation metrics and monitoring strategies for AI model performance, accuracy, hallucination detection, and response quality.
Collaborate with cross-functional teams including Data Science, ML Engineering, and Product teams.
Assist in developing and improving agentic workflows and AI agent orchestration systems.
Troubleshoot and optimize AI pipeline performance and workflow reliability.
Document architecture, evaluation methodologies, and operational procedures.
Required Skills
Strong experience in AI/LLM evaluation pipelines.
Hands-on experience with AI evaluation frameworks and benchmarking methodologies.
Experience developing automation workflows and scheduled pipeline jobs.
Strong experience working in Databricks environments.
Proficiency in Python and AI/ML ecosystem tools.
Experience with REST APIs, workflow orchestration, and data processing pipelines.
Understanding of prompt evaluation, hallucination detection, and model performance analysis.
Preferred / Nice-to-Have Skills
Experience with agentic workflows and AI agent development.
Hands-on experience creating AI agents and orchestration systems.
Experience with LangGraph.
Experience with RAGAS and RAG evaluation frameworks.
Experience supporting and optimizing RAG pipelines.
ADP platform experience is a plus.
Technical Environment
Python
Databricks
LangGraph
RAGAS
LLM Evaluation Frameworks
AI/ML Pipelines
Agentic AI Workflows
RAG Architectures
Automation & Scheduling Tools
Qualifications
Bachelor’s or Master’s degree in Computer Science, Data Science, AI, or related field.
Proven experience in Generative AI, Machine Learning, or AI Engineering roles.
Strong analytical and problem-solving skills.
Excellent communication and collaboration abilities.