AI Solutions Engineer: LLMs, Multi-Agent Workflows & APIs

Innorev Technologies Inc; Charlotte (NC); On-site; USD 120,000 - 160,000; Full time

Job summary

Innorev Technologies Inc in Charlotte, NC designs and builds agentic AI solutions using LLMs like GPT, Azure OpenAI, and Claude. You will develop multi-agent workflows with planning, memory, and tool-use capabilities to automate complex tasks.

The role involves integrating APIs, enterprise systems, and knowledge sources into AI workflows, devising prompt strategies and RAG pipelines, and optimizing vector-based retrieval with FAISS, Pinecone, and Azure AI Search while ensuring scalable REST APIs

Qualifications

• Design and develop agentic AI solutions with LLMs.
• Develop multi-agent workflows with planning, memory, and tool-use.
• Integrate APIs and enterprise systems into AI workflows.
• Develop prompt strategies and RAG pipelines.
• Build AI solutions using vector databases.

Responsibilities

• Design and develop agentic AI solutions using LLMs such as GPT, Azure OpenAI, and Claude.
• Build multi-agent workflows with planning, memory, and tool-use capabilities.
• Integrate APIs, enterprise systems, and knowledge sources into AI workflows.
• Develop prompt engineering strategies and implement RAG pipelines.
• Build and optimize AI solutions using vector databases such as FAISS, Pinecone, and Azure AI Search.
• Develop REST APIs and microservices while ensuring scalability, security, and performance.

Skills

Python

LangChain

Semantic Kernel

AutoGen

CrewAI

RAG

LLMs

Prompt Engineering

Embeddings

Vector Databases

REST APIs

Microservices

Azure AI

AWS AI Services

Tools

FAISS

Pinecone

Azure AI Search

Azure OpenAI

Job description

Innorev Technologies Inc in Charlotte, NC designs and builds agentic AI solutions using LLMs like GPT, Azure OpenAI, and Claude. You will develop multi-agent workflows with planning, memory, and tool-use capabilities to automate complex tasks.

The role involves integrating APIs, enterprise systems, and knowledge sources into AI workflows, devising prompt strategies and RAG pipelines, and optimizing vector-based retrieval with FAISS, Pinecone, and Azure AI Search while ensuring scalable REST APIs