AI/ML Engineer

ASSYST, Inc.•Austin, TX

8h•Hybrid

About The Position

ASSYST is seeking a skilled AI/ML Engineer (AI Agent Engineer) to support our client project in Austin, TX. This is a hybrid position. We are looking for a highly experienced professional to design, develop, and deploy intelligent AI-driven solutions that enhance business productivity and decision-making. The role focuses on building autonomous agentic systems, Retrieval-Augmented Generation (RAG) architectures, and scalable AI workflows, with a strong emphasis on governance, security, and cost efficiency. The ideal candidate will collaborate closely with developers, UX designers, and business and systems analysts to research, design, implement, and continuously improve AI-powered applications.

Requirements

4+ years of experience in AI/ML engineering or advanced data science.
Proven experience building and deploying production-grade autonomous agents.
Strong expertise in context engineering.
Hands-on experience with 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.
Strong understanding of AI governance, model lifecycle management, and evaluation.
Experience implementing and extending Model Context Protocol (MCP).
Experience with AI guardrails, content filtering, and safety controls.
Knowledge of data privacy practices, including handling sensitive data (PII/PHI).
2+ years of experience building multi-agent or autonomous workflows.
Experience optimizing LLM cost, token usage, and performance.
Familiarity with enterprise AI deployment patterns, scalability, and distributed systems.

Responsibilities

Design, develop, and manage AI/ML software programs, including autonomous agents and intelligent workflows.
Build and deploy production-grade AI agent systems using modern frameworks and tools.
Implement and optimize Retrieval-Augmented Generation (RAG) architectures using vector databases.
Integrate Large Language Models (LLMs) via APIs to enable advanced AI capabilities.
Develop and maintain context engineering strategies to improve model performance and accuracy.
Implement AI governance practices, including model lifecycle management, monitoring, and evaluation.
Apply AI safety measures such as guardrails, content filtering, and responsible AI controls.
Extend and implement Model Context Protocol (MCP) for secure access to local and remote data sources.
Collaborate with cross-functional teams to translate business requirements into AI-driven solutions.
Test, evaluate, and optimize AI models and systems for performance, scalability, and cost efficiency.