Software Engineer: AI Orchestrator

*Overview*

Ensure all your application information is up to date and in order before applying for this opportunity.
We seek a software engineer to orchestrate knowledgebase creation and integration with advanced, customized LLMs. This role involves developing and maintaining high-quality datasets essential for advancing artificial intelligence and machine learning applications. The software engineer will automate digitization and preparation of large volumes of textual material for use in AI training and research systems. The role's primary responsibility is to architect *digital workflow management*, including labeling, classification, and structured ingestion into database and vector-storage systems.

*Data Curation & Workflow Automation*

* Run semi-automated pipelines for OCR, metadata extraction, text cleaning, labeling, and semantic classification
* Use internal tools (scripts, command-line tools, tagging interfaces) to prepare data for downstream AI use
* Curate datasets to ensure accuracy, remove duplicates, and verify quality
* Segment books into chapters, pages, or logical units suitable for vector embedding
* Use AI tools to parse textual data into semantic units and knowledge trees

*Database & Vector Store Operations*

* Assist in loading processed text into vector databases (e.g., Chroma, Pinecone, Milvus, Weaviate)
* Verify embedding quality and troubleshoot ingestion errors
* Maintain structured data inventories and documentation

*Document Digitization*

* Oversee the scaning of books, manuscripts, bound documents, and loose-leaf archives using professional scanning equipment
* Ensure image quality, alignment, OCR readability, and version consistency
* Organize and catalog scanned material according to established metadata standards
* Customize OCR processes to recognize symbols and special typography

*Required Skills*

* Software process and algorithmic design
* AI orchestration xhqgsiq and workflow scripting
* Coding in standard languages such as C and Python

*Preferred Skills*

* Experience with OCR tools
* Familiarity with Linux, command-line utilities, or basic scripting (Python, Bash)
* Understanding of text processing, metadata standards, or digitization workflows
* Experience with vector databases or AI embedding workflows
* Experience with AI-related programming tools and methods
* Interest in AI, LLMs, or digital humanities

Pay: $120,000.00 - $160,000.00 per year

Benefits:
* Health insurance
* Relocation assistance

Work Location: In person