Semantic Data Engineer

This is a fully remote position, open to applicants in Colorado, +12 more states.

📋 Description

• Collaborate with data subject matter experts and business users to thoroughly understand and model their areas of expertise.

• Utilize NLP techniques (such as entity extraction, classification, and document processing) to convert raw data and content into AI-ready resources.

• Design, implement, test, and manage comprehensive RAG workflows for client projects, encompassing retrieval pipeline architecture, embedding strategies, and response evaluation.

• Participate in the design and implementation of agentic AI solutions, including orchestration patterns, tool utilization, and memory and retrieval integration.

• Assist in various business intelligence initiatives using AI-driven solutions.

• Analyze complex datasets and convey insights to both technical and non-technical audiences.

• Create and implement data pipelines for ingesting, processing, and enhancing structured and unstructured content using SQL, Python, R, or equivalent languages.

• Contribute to the development of semantic layers and knowledge graph implementations as part of broader AI solution architectures.

• Collaborate with internal and external teams to contextualize data engineering efforts within larger project frameworks.

⛳️ Requirements

• Bachelor’s degree in mathematics, statistics, economics, data science, computer science, or a related discipline.

• Over 5 years of experience in data analysis projects, focusing on report design and developing data analysis methodologies and visualizations in a production environment.

• Demonstrated experience in direct client engagement, including delivering briefings, facilitating meetings, and presenting deliverables.

• Expertise in applying machine learning techniques and statistical analyses to business applications.

• Proficient in programming languages such as Python, R, or similar for data analysis and modeling tasks.

• Experience with NLP methodologies: entity extraction, text classification, document processing, or comparable techniques applied to unstructured data in production environments.

• Practical experience in constructing and optimizing RAG pipelines, including embedding strategies, reranking, and cross-encoder models.

• Familiarity with retrieval quality and evaluation metrics (such as precision, recall, MRR, and user-centric evaluation methods).

• Experience in implementing monitoring and observability for RAG and AI components, addressing latency, success rates, cache hit rates, retrieval quality, and data drift.

• Understanding of data modeling, database architecture, and data integration, aggregation, and normalization across diverse sources.

• Desire to develop as a consultant and take on additional responsibilities for delivering and expanding work.

🏝️ Benefits

• Competitive salary and performance-based bonuses.

• Opportunities for professional development and continuous learning.

• Flexible work environment and remote work options.

• Comprehensive health and wellness benefits.

• Collaborative and innovative work culture.