AI Knowledge Data Engineer

TL;DR

AI Knowledge Data Engineer: Designing, implementing, and scaling state-of-the-art AI systems that combine large language models (LLMs), advanced retrieval techniques, cognitive memory architectures, knowledge representation, and data fusion. Orchestrating robust data pipelines and architecting scalable training data solutions. Focus on building foundational knowledge bases for next-generation AI agents, ensuring systems efficiently retrieve, contextualize, and generate accurate information for diverse business applications, and designing cognitive memory systems for AI agents.

Location: Remote or Hybrid in Bulgaria

Company

iBusinessFunding is a leader in providing innovative SaaS solutions for banks and lenders, specializing in SBA lending, and processing over $7 billion in SBA loans.

What you will do

• Architect, implement, and optimize retrieval-augmented generation (RAG) workflows by integrating local LLMs with retrieval mechanisms.
• Design, build, and maintain scalable data pipelines for ingesting, transforming, and indexing structured and unstructured data.
• Orchestrate and scale training data operations, including data curation and lineage tracking for large-scale LLM training and fine-tuning.
• Develop and maintain ontologies, knowledge graphs, and semantic data models to structure and integrate domain-specific knowledge.
• Implement and optimize knowledge retrieval strategies and aggregate disparate knowledge bases into a fused approach.
• Design cognitive memory systems for AI agents, enabling persistent knowledge retention and contextual awareness.

Requirements

• Bachelor’s or Master’s degree in Computer Science, Data Science, Machine Learning, or a related field.
• Proven experience designing and scaling data pipelines and training data workflows for LLMs or similar AI systems.
• Strong background in information retrieval systems, vector search technologies, and RAG frameworks (e.g., FAISS, Pinecone, Elasticsearch, Milvus).
• Proficiency in programming (Python) and machine learning libraries (TensorFlow, PyTorch).
• Experience with ontologies, knowledge graphs, and semantic technologies (RDF, OWL, SPARQL).
• Familiarity with distributed data processing and orchestration tools (e.g., Spark, Airflow, Kubeflow).

Nice to have

• Experience with LLM fine-tuning, prompt engineering, and RAG optimization.
• Familiarity with data-centric AI principles and training data quality assessment.
• Experience with cloud platforms and scalable storage solutions.
• Background in cognitive memory architectures or AI agent design.

Culture & Benefits

• Great work-life balance.
• Competitive remuneration package.
• Exceptional social package & special discounts.
• Supplemental health & dental care.
• Team bonding events, excellent office location & facilities, relaxing & gaming areas, free bike parking & showers.