AI Engineer

Elios, Inc.; Dallas, Northern (TX, KY); Hybrid; USD 83,000 - 152,000; Full time

Job summary

Elios, Inc. in Dallas, TX is hiring an AI Engineer for a hands-on onsite contract role to build production GenAI applications and agentic systems connected to enterprise data.

You will design, implement, and deploy LLM-powered services and autonomous agents in real operating environments. The work focuses on GraphRAG architectures, embeddings, and enterprise-grade reliability with Python, FastAPI, and Docker across cloud platforms.

Qualifications

• At least 5 years of AI/ML software engineering experience.
• Shipped production GenAI or agentic AI systems.
• Strong knowledge of embeddings, ontologies and knowledge graphs.

Responsibilities

• Build GenAI services in Python with FastAPI and scalable REST APIs.
• Deploy and manage Docker workloads across cloud providers (AWS, Azure, GCP).
• Set up LLM evaluation workflows with LangSmith and Ragas.
• Lead CI/CD, monitoring, and reliability for end-to-end GenAI apps.

Skills

AI/ML engineering

Production LLMs

MLOps

Embeddings

CI/CD

Tools

Python

FastAPI

Docker

REST APIs

LangSmith

Ragas

Job description

GraphRAG Agent orchestration RAG LLMOps LangSmith Ragas Knowledge graphs Ontology extraction Embeddings FastAPI LLM evaluation Enterprise data integration Python Docker AWS Azure GCP CI/CD REST APIs MLOps Full-stack development

Job Description

We're hiring an AI Engineer for a contract role in Dallas, Texas. This is a hands-on, onsite position focused on building production GenAI applications and agentic systems that connect to enterprise data and reach end users in real operating environments. You'll design, build, and deploy LLM-powered applications and autonomous AI agents, with a strong focus on GraphRAG, advanced RAG architectures, and enterprise-grade reliability.

The work includes building GenAI services in Python with FastAPI, developing scalable REST APIs, deploying workloads with Docker across AWS, Azure, and GCP, and supporting full-stack delivery when needed. You'll also set up LLM evaluation workflows using tools such as Ragas, LangSmith, and custom benchmarks to measure groundedness, relevance, and hallucination rates.

This role also covers LLMOps and MLOps practices, including CI/CD, prompt and version management, automated testing, and monitoring for latency, cost, and response quality. The right person brings at least 5 years of AI/ML-focused software engineering experience and has shipped production LLM or agentic AI systems that made it past the demo stage. Strong experience with embeddings, knowledge graphs, ontology extraction, and enterprise data integration is important, along with the ability to help shape architecture and delivery standards for modern GenAI systems.