Request Technology - Chicago, IL

posted 2 months ago

Full-time
Chicago, IL
Administrative and Support Services

About the position

As an Artificial Intelligence (AI) Engineer, you will play a pivotal role in developing and implementing AI solutions that enhance business workflows and drive innovation. This position requires a strong foundation in AI engineering, particularly at the enterprise level, with a focus on natural language processing (NLP) and machine learning. You will be responsible for prototyping and testing AI solutions using Python and Streamlit, specifically targeting text extraction from various document types. Your expertise in AI engineering tools such as Langchain, LlamaIndex, and Semantic Kernel will be crucial in developing plugins and assistants that leverage prompt engineering and semantic function design. In this role, you will design and implement Retrieval Augmented Generation (RAG) stores, integrating classic information retrieval techniques with modern semantic embeddings stored in vector and graph databases. You will also develop and deploy agents using AutoGen, CrewAI, LangChain Agents, and LlamaIndex Agents, utilizing Generative AI to extract metadata and insights from documents. Fine-tuning large language models (LLMs) to optimize performance for specific domains and cost efficiency will be a key responsibility. Collaboration with stakeholders is essential as you will work to implement and automate AI-powered solutions that streamline common business workflows. Additionally, you will enhance documentation procedures and codebases, ensuring adherence to best practices that promote knowledge sharing and maintain an organized and reproducible working environment. This hybrid position requires you to be on-site 3-5 days a week in Chicago, IL, and is not open to C2C, contract, or contract-to-hire arrangements.

Responsibilities

  • Prototype and test AI solutions using Python and Streamlit with a focus on natural language processing and text extraction from documents (PyPDF, Azure Document Intelligence)
  • Develop plugins and assistants using LangChain, LlamaIndex, or Semantic Kernel, with expertise in prompt engineering and semantic function design
  • Design and implement Retrieval Augmented Generation (RAG) stores using a combination of classic information retrieval and semantic embeddings stored in vector and graph databases
  • Develop and deploy agents using AutoGen, CrewAI, LangChain Agents, and LlamaIndex Agents
  • Use Gen AI to distill metadata and insights from documents
  • Fine tune LLMs to optimize for domain and cost
  • Collaborate with stakeholders to implement and automate AI powered solutions for common business workflows
  • Enhance documentation procedures, codebase, and adherence to best practices to promote and facilitate knowledge sharing and ensure the upkeep of an organized and reproducible working environment

Requirements

  • Bachelor's degree required; master's degree preferred
  • 5+ years of experience in AI engineering at the enterprise level
  • Experience with AI engineering tools and technologies, including Python, Langchain, LlamaIndex, and Semantic Kernel
  • Strong understanding of large language models
  • Experience with natural language processing, text extraction, and information retrieval techniques
  • Strong understanding of machine learning and deep learning concepts including transformer based GPT models
  • Experience with distributed computing and cloud environments (e.g., Microsoft Azure)
© 2024 Teal Labs, Inc
Privacy PolicyTerms of Service