Principal AI Engineer: Generative AI & LLM Orchestration

Artifintech; Waukesha (WI); On-site; USD 180,000 - 280,000; Full time

Benefits offered by this job

Equal opportunity employer

Job summary

ARTIFICIAL INTELLIGENCE TECHNOLOGIES LLC seeks a Principal AI Engineer to lead architecture and deployment of Generative AI solutions. You will build advanced AI agents and integrate large language models into enterprise ecosystems to solve complex business challenges.

Key responsibilities include scalable solution design with LangChain and AutoGen, multi-agent orchestration with memory and reasoning, LLM performance optimization, and cloud pipelines on AWS/Azure/GCP.

Qualifications

• 12+ years of software engineering and data science experience.
• Expert Python programming and backend integration.
• Deep expertise in LLMs such as GPT and Claude.
• Experience with LangChain, AutoGen and vector databases.
• Knowledge of MLOps and cloud deployment pipelines.
• Industry certifications in AI or cloud architecture.

Responsibilities

• Design and implement scalable AI solutions using LangChain and AutoGen.
• Develop multi-agent orchestration systems with memory and reasoning.
• Optimize LLM performance via prompting and hyperparameter tuning.
• Architect robust pipelines on AWS/Azure/GCP for model deployment.
• Collaborate with cross-functional teams to embed AI into products.

Skills

LangChain

Microsoft AutoGen

LlamaIndex

Prompt Engineering

RAG

Agentic Orchestration

Fine-tuning

Python

LLM (GPT/Claude)

Orchestration Tools

Agentic Frameworks

Vector Databases

MLOps

Cloud Platforms (AWS/Azure/GCP)

Job description

ARTIFICIAL INTELLIGENCE TECHNOLOGIES LLC seeks a Principal AI Engineer to lead architecture and deployment of Generative AI solutions. You will build advanced AI agents and integrate large language models into enterprise ecosystems to solve complex business challenges.

Key responsibilities include scalable solution design with LangChain and AutoGen, multi-agent orchestration with memory and reasoning, LLM performance optimization, and cloud pipelines on AWS/Azure/GCP.