Principal AI Engineer — Generative AI & LLM Orchestration

Valiant Technologies LLC; Waukesha (WI); On-site; USD 180,000 - 230,000; Full time

Job summary

VALIANT TECHNOLOGIES LLC seeks a Principal AI Engineer to lead architecture and deployment of advanced Generative AI solutions. You will build sophisticated AI agents and integrate high-scale LLMs into enterprise ecosystems to solve complex business challenges.

Key responsibilities include designing scalable AI solutions with LangChain and AutoGen, developing multi-agent orchestration with memory and reasoning, and optimizing LLM performance via prompt engineering and tuning.

Qualifications

• 12+ years of software engineering and data science experience.
• Expert proficiency in Python programming and backend integration.
• Deep expertise in Large Language Models (LLM) such as GPT and Claude.
• Proven experience with orchestration tools and agentic frameworks.
• Knowledge of MLOps for automating model deployments.
• Relevant certifications in AI or cloud architecture.

Responsibilities

• Design and implement scalable AI solutions using LangChain and AutoGen.
• Develop multi-agent orchestration systems with advanced memory and reasoning capabilities.
• Optimize LLM performance through prompt engineering and hyperparameter tuning.
• Architect robust pipelines on cloud platforms (AWS, Azure, or GCP) to support AI deployment.
• Collaborate with cross-functional teams to integrate AI into existing digital products.

Skills

Prompt Engineering

RAG

Agent Memory

Fine-tuning

Python

LLMs

GPT

Claude

Education

Bachelor's degree or higher in CS/related

Tools

LangChain

Microsoft AutoGen

LlamaIndex

AWS

Azure

GCP

Job description

VALIANT TECHNOLOGIES LLC seeks a Principal AI Engineer to lead architecture and deployment of advanced Generative AI solutions. You will build sophisticated AI agents and integrate high-scale LLMs into enterprise ecosystems to solve complex business challenges.

Key responsibilities include designing scalable AI solutions with LangChain and AutoGen, developing multi-agent orchestration with memory and reasoning, and optimizing LLM performance via prompt engineering and tuning.