AI Engineer: LLM Apps, Prompting & Agent Orchestration

Qualis1 Inc.; Mount Laurel Township (NJ); On-site; USD 120,000 - 180,000; Full time

Job summary

Qualis1 Inc. seeks an AI-focused software engineer to develop LLM-powered applications in a Mount Laurel, NJ environment. You will craft prompts, design multi-step, multi-agent workflows, and integrate advanced AI tooling (LangChain, AutoGen, CrewAI) with RAG pipelines and vector databases.

You will translate business use cases into scalable AI solutions while applying networking knowledge (L2/L3) to optimize performance and latency, supporting cost-efficient AI deployments.

Qualifications

• Proven experience in building generative AI/LLM-powered apps.
• Strong prompt engineering and evaluation for quality, cost and latency.
• Experience with agentic AI and multi-step workflows.
• Proficiency with LangChain, AutoGen, and CrewAI tooling.
• Hands-on with vector databases, embeddings, and RAG pipelines.
• Strong Python development skills; experience with FastAPI and REST APIs.

Responsibilities

• Build LLM-powered applications with advanced prompt engineering.
• Develop agentic applications—tool-calling and multi-step workflows.
• Integrate LLM APIs and RAG pipelines into production systems.
• Evaluate and iterate prompts/workflows for quality, cost, and latency.
• Translate business use cases into scalable AI solutions.
• Apply networking domain knowledge (L2/L3) to AI solutions.

Skills

Generative AI

LLMs

Prompt Engineering

Agentic AI

LangChain

AutoGen

CrewAI

RAG

Vector Databases

Embeddings

Azure OpenAI

OpenAI APIs

Python

FastAPI

REST APIs

AI Orchestration

Multi-Agent Systems

Cost Optimization

SDWAN

L2/L3 Networking

Routing & Switching

Network Automation

Solution Architecture

Tools

LangChain

AutoGen

CrewAI

Embeddings

Vector Databases

Azure OpenAI

OpenAI APIs

Python

FastAPI

REST APIs

Job description

Qualis1 Inc. seeks an AI-focused software engineer to develop LLM-powered applications in a Mount Laurel, NJ environment. You will craft prompts, design multi-step, multi-agent workflows, and integrate advanced AI tooling (LangChain, AutoGen, CrewAI) with RAG pipelines and vector databases.

You will translate business use cases into scalable AI solutions while applying networking knowledge (L2/L3) to optimize performance and latency, supporting cost-efficient AI deployments.