AI Engineer

Request Technology - Chicago, IL

Full-time - Mid Level

Chicago, IL

Administrative and Support Services

About the position

The AI Engineer will be a key member of the AI Engineering team, focusing on the development and implementation of advanced AI solutions, particularly in the areas of natural language processing and machine learning. This role aims to enhance efficiency and decision-making across various business and legal practices by leveraging both structured and unstructured data. The engineer will prototype and test innovative solutions, collaborate with stakeholders, and ensure best practices in documentation and code management.

Responsibilities

• Develop and implement cutting-edge legal AI solutions that drive efficiency and improve decision making.
• Prototype and test AI solutions using Python and Streamlit, focusing on natural language processing and text extraction from documents.
• 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 classic information retrieval and semantic embeddings.
• 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.

Requirements

• Bachelor's Degree in Computer Science, Engineering, or related field.
• A minimum of 5 years of experience in AI engineering or a related field.
• Proven experience with AI engineering tools and technologies, including Python, Streamlit, Jupyter Notebooks, Langchain, LlamaIndex, and Semantic Kernel.
• 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).
• Solid understanding of large language models.