You are viewing a preview of this job. Log in or register to view more details about this job.

AI Engineer

Job Title: AI Engineer (Part-Time or Full-Time)
Location: Columbia, MD (Onsite)

Role Overview:

We are seeking a highly motivated and technically proficient AI Engineer to join our team in Columbia, MD. In this role, you will work on leveraging cutting-edge AI and large language models (LLMs) to extract, structure, and integrate information from complex documents. Your work will directly support the development of AI-powered tools and workflows that improve document understanding and automation across critical domains.

 

Key Responsibilities:

  • Design and apply prompts for LLMs (e.g., GPT, Claude) to extract structured insights from unstructured text.
  • Convert free-form content into structured formats such as JSON, tables, or domain-specific templates.
  • Write, test, and iterate on prompt engineering strategies for optimal model performance.
  • Build lightweight tools or scripts for reviewing, validating, and automating AI model outputs.
  • Track provenance of extracted information to ensure traceability and auditability.
  • Collaborate with software engineers and product teams to integrate AI components into production workflows.
  • Evaluate and benchmark AI outputs using structured test cases and quality metrics.

 

Required Skills & Qualifications:

  • 1+ years of hands-on experience in AI/ML, preferably focused on natural language processing (NLP) or document intelligence.
  • Practical experience working with large language models (LLMs) such as OpenAI GPT, Anthropic Claude, or similar.
  • Proficiency in Python and libraries/frameworks such as LangChain, spaCy, Hugging Face Transformers, or similar.
  • Knowledge of document preprocessing techniques: chunking, embeddings, vectorization, etc.
  • Experience working with vector databases like FAISS, Chroma, Pinecone, or equivalent.
  • Ability to design structured experiments and test plans to assess AI behavior and output accuracy.

 

Preferred Qualifications:

  • Experience implementing Retrieval-Augmented Generation (RAG) pipelines.
  • Familiarity with processing compliance, regulatory, or legal documents.
  • Understanding of web APIs, data pipelines, and LLMOps practices.
  • Exposure to prompt versioning, logging, and AI output traceability techniques.