NEWPosted 2 hours ago

Job ID: JOB_ID_7694

About the Role:

The Department of Information Resources (DIR) is seeking three experienced Software Developer 2 candidates to serve as AI Agent Engineers. This role involves researching, designing, implementing, and managing advanced AI-driven agentic solutions. The primary focus will be on developing autonomous workflows and Retrieval-Augmented Generation (RAG) systems to boost productivity, automate processes, and support intelligent decision-making, with a strong emphasis on governance, security, and cost efficiency.

Key Responsibilities:

  • Design, develop, and deploy production-grade autonomous AI agents.
  • Implement Retrieval-Augmented Generation (RAG) architectures using vector databases.
  • Develop and manage AI-driven workflows and intelligent decision-making systems.
  • Integrate Large Language Models (LLMs) via APIs, leveraging libraries like OpenAI, Hugging Face, and Azure AI.
  • Implement AI guardrails, content filtering, and safety controls to ensure responsible AI deployment.
  • Manage context engineering and optimize LLM cost, token usage, and performance.
  • Ensure data privacy and secure handling of sensitive data (PII/PHI).
  • Collaborate with cross-functional teams, including UX designers, business analysts, and other developers.
  • Stay current with advancements in AI/ML, LLMs, and agentic systems.
  • Contribute to the development of AI governance frameworks and model lifecycle management.

Required Skills and Qualifications:

  • 4 years of experience in AI/ML engineering or advanced data science.
  • Proven track record of building and deploying production-grade autonomous agents.
  • Strong experience in context engineering.
  • Deep experience with AI frameworks such as LangChain, LangGraph, CrewAI, or AutoGPT.
  • Experience implementing RAG architectures using vector databases.
  • Proficiency in Python and AI/ML libraries (OpenAI, Hugging Face, Azure AI).
  • Experience integrating LLMs via APIs.
  • Knowledge of AI governance, model lifecycle management, and evaluation.
  • Experience implementing AI guardrails, content filtering, and safety controls.
  • Understanding of data privacy and handling of sensitive data (PII/PHI).

Preferred Skills:

  • 2 years of experience building multi-agent or autonomous agentic workflows.
  • Experience optimizing LLM cost, token usage, and performance.
  • Familiarity with enterprise AI deployment patterns and scalability considerations.

Work Environment:

The primary work location is 4601 W Gudalupe St, Austin, Texas 78751. This is a hybrid position, requiring 2 days onsite (Tuesdays and Wednesdays) and offering 3 days of remote work. Candidates must be LOCAL TO THE AUSTIN AREA ONLY (within a 50-mile radius) and must already reside in Texas. Candidates planning to move to Texas will not be considered.

Contract Details:

The estimated start date is 04/30/2026, with an expected completion date of 08/31/2026. The total estimated hours per candidate will not exceed 780 hours. This service may be amended, renewed, or extended upon mutual agreement.

About the Hiring Organization:

The Department of Information Resources (DIR) is responsible for overseeing the state’s information resources. This is an opportunity to contribute to critical state initiatives.


Special Requirements

Visa Constraints: None specified. Screening Steps: Not explicitly detailed, but implies candidate evaluation based on skills. Interview Modes: Not specified, likely standard interview process. Domain Restrictions: Candidates must be LOCAL TO THE AUSTIN AREA ONLY (Within 50-mile radius) and must already reside in Texas.


Compensation & Location

Salary: $120,000 – $170,000 per year

Location: Austin, TX


Recruiter / Company – Contact Information

Recruiter / Employer: Department of Information Resources (DIR)

Email: yanka@triwavesolutions.com


Interested in this position?
Apply via Email

Recruiter Notice:
To remove this job posting, please send an email from
yanka@triwavesolutions.com with the subject:

DELETE_JOB_ID_7694

to delete@join-this.com.