AI Engineer (LLM & Autonomous Systems)
Role summary
Seeking an AI Engineer for a contract role (May-August 2026) in Austin, TX, focusing on designing and developing next-generation AI solutions. This hybrid position involves building LLM-driven applications, agent-based architectures, and RAG systems to enhance automation and efficiency. Responsibilities include integrating LLMs via APIs, implementing agentic frameworks, developing RAG pipelines, and ensuring AI governance, security, and compliance. The ideal candidate will have 4+ years of AI/ML engineering experience, proficiency in Python and AI/ML libraries, and hands-on experience with frameworks like LangChain. Experience with AI safety mechanisms and data privacy is crucial.
Location:
Austin, TX (Hybrid – Local Candidates Only)
Duration:
May 2026 – August 2026 (Extension Possible)
Schedule:
Monday–Friday, 8:00 AM – 5:00 PM CST
Hours:
Up to 780 hours
Overview
We are seeking a skilled
AI Engineer
to design and develop next-generation AI-powered solutions, including autonomous workflows and intelligent systems.
This role focuses on building
LLM-driven applications, agent-based architectures, and Retrieval-Augmented Generation (RAG) systems
to improve automation, decision-making, and operational efficiency. The ideal candidate will have hands-on experience developing production-grade AI systems with strong attention to governance, security, and scalability.
Key Responsibilities
AI & Agent Development
- Design and build AI-driven applications, including autonomous agents and multi-step workflows
- Develop and deploy Retrieval-Augmented Generation (RAG) pipelines using vector databases
- Implement agentic frameworks for task automation and decision support
LLM Integration & Engineering
- Integrate large language models (LLMs) via APIs (OpenAI, Azure AI, Hugging Face)
- Apply advanced prompt engineering and context management techniques
- Optimize model performance, token usage, and cost efficiency
Platform & Architecture
- Design scalable and secure AI architectures for enterprise environments
- Implement Model Context Protocol (MCP) or similar frameworks for structured data access
- Support multi-agent orchestration and distributed AI workflows
Governance, Security & Compliance
- Implement AI guardrails, content filtering, and safety controls
- Ensure compliance with data privacy standards (PII/PHI handling)
- Support model lifecycle management, evaluation, and monitoring
Collaboration & Delivery
- Work closely with developers, UX designers, and business analysts
- Participate in design, development, testing, and deployment cycles
- Contribute to best practices for enterprise AI adoption
Required Qualifications
- 4+ years of experience
in AI/ML engineering or advanced data science
- Proven experience building and deploying
production-grade AI agents or LLM applications
- Strong experience with
context engineering and prompt design
- Hands-on experience with frameworks such as:
- LangChain, LangGraph, CrewAI, or AutoGPT
- Experience implementing
RAG architectures with vector databases
- Proficiency in
Python and AI/ML libraries
(OpenAI, Hugging Face, Azure AI)
- Experience integrating LLMs via APIs
- Strong understanding of:
- AI governance, model lifecycle management, and evaluation
- Data privacy and handling sensitive data (PII/PHI)
- Experience implementing AI safety mechanisms (guardrails, filtering, controls)
Preferred Qualifications
- Experience building
multi-agent or autonomous AI workflows
- Experience optimizing LLM cost, latency, and token usage
- Familiarity with enterprise AI deployment and scalability patterns
- Knowledge of data architectures supporting AI systems
Work Requirements
- Must be
local to Austin, TX
(no relocation candidates)
- Hybrid work environment (onsite + remote flexibility)
- Occasional after-hours or weekend work may be required
- In-person interview required