AI Engineer

Elios, Inc.; Charlotte (NC); Hybrid; USD 120,000 - 170,000; Part time

Job summary

Elios, Inc. is seeking an experienced AI/ML software engineer to build production-grade GenAI applications and autonomous AI agents for large enterprise environments in Charlotte, NC.

The role focuses on GraphRAG architectures, embeddings at scale, and LLM-powered services designed for production-scale deployment. You will design and deploy Python/FastAPI services, build REST APIs for LLM-driven applications, and work with knowledge graphs, embeddings, and ontology extraction, deploying

Qualifications

• 5+ years of AI/ML oriented software engineering experience.

Responsibilities

• Design and deploy Python/FastAPI services for LLM-driven applications.

Skills

AI/ML software engineering

GenAI development

LLM services

Embeddings

Knowledge graphs

Ontology extraction

CI/CD

Prompt versioning

Testing

Monitoring

Tools

Python

FastAPI

REST APIs

Docker

AWS

Azure

GCP

Ragas

LangSmith

CI/CD

Job description

GraphRAG Agentic workflows RAG Knowledge graphs Ontology extraction LLM evaluation Ragas LangSmith Embeddings LLMOps MLOps Prompt versioning Python FastAPI REST APIs Docker AWS Azure GCP CI/CD Full-stack development

Job Description

Location: Charlotte, NC | Type: Contract | Experience: 5+ years

This onsite contract role is focused on building production-grade GenAI applications and autonomous AI agents for large enterprise environments. You'll work on GraphRAG and advanced RAG architectures, enterprise data integration, and LLM-powered services that need to scale in production, not just look good in a demo.

The work includes designing and deploying Python/FastAPI services, building REST APIs for LLM-driven applications, and working with embeddings at scale, knowledge graphs, and ontology extraction. You'll also deploy workloads across AWS, Azure, and GCP.

There is a strong emphasis on evaluation and operational discipline. That includes implementing LLM evaluation frameworks with tools like Ragas and LangSmith, or custom benchmarks, to measure relevance, groundedness, and hallucination. You'll also apply LLMOps and MLOps practices such as CI/CD, prompt and version management, automated testing, and monitoring across latency, cost, and response quality.

The right person brings 5+ years of AI/ML-oriented software engineering experience and a track record of shipping production LLM or agentic systems.