Architect and optimize LLM-based systems, including RAG pipelines, vector databases, and agentic AI frameworks (e.g., LangChain, AutoGen). * Design and evolve the AI/ML platform architecture ...
Quick apply
Architect and optimize LLM-based systems, including RAG pipelines, vector databases, and agentic AI frameworks (e.g., LangChain, AutoGen). * Design and evolve the AI/ML platform architecture ...
Architect and optimize LLM-based systems, including RAG pipelines, vector databases, and agentic AI frameworks (e.g., LangChain, AutoGen). * Design and evolve the AI/ML platform architecture ...
Architect and optimize LLM-based systems, including RAG pipelines, vector databases, and agentic AI frameworks (e.g., LangChain, AutoGen). * Design and evolve the AI/ML platform architecture ...
MFG AI Solution Architect
Georgetown, KY · On-site
$57 - $75/hr
... and vector databases (OpenSearch/Pinecone) • Support the architecture and enablement of the Manufacturing Data Hub and Analytics Workbench • Integrate AI models into production systems and ...
MFG AI Solution Architect
Georgetown, KY · On-site
$57 - $75/hr
... and vector databases (OpenSearch/Pinecone) • Support the architecture and enablement of the Manufacturing Data Hub and Analytics Workbench • Integrate AI models into production systems and ...
Architect and optimize LLM-based systems, including RAG pipelines, vector databases, and agentic AI frameworks (e.g., LangChain, AutoGen). * Design and evolve the AI/ML platform architecture ...
Quick apply
Architect and optimize LLM-based systems, including RAG pipelines, vector databases, and agentic AI frameworks (e.g., LangChain, AutoGen). * Design and evolve the AI/ML platform architecture ...
Architect and optimize LLM-based systems, including RAG pipelines, vector databases, and agentic AI frameworks (e.g., LangChain, AutoGen). * Design and evolve the AI/ML platform architecture ...
Architect and optimize LLM-based systems, including RAG pipelines, vector databases, and agentic AI frameworks (e.g., LangChain, AutoGen). * Design and evolve the AI/ML platform architecture ...
Architect and optimize LLM-based systems, including RAG pipelines, vector databases, and agentic AI frameworks (e.g., LangChain, AutoGen). * Design and evolve the AI/ML platform architecture ...
Architect and optimize LLM-based systems, including RAG pipelines, vector databases, and agentic AI frameworks (e.g., LangChain, AutoGen). * Design and evolve the AI/ML platform architecture ...
Architect and optimize LLM-based systems, including RAG pipelines, vector databases, and agentic AI frameworks (e.g., LangChain, AutoGen). * Design and evolve the AI/ML platform architecture ...
Architect and optimize LLM-based systems, including RAG pipelines, vector databases, and agentic AI frameworks (e.g., LangChain, AutoGen). * Design and evolve the AI/ML platform architecture ...
Design Retrieval-Augmented Generation (RAG) architectures, vector databases, prompt engineering frameworks, and enterprise knowledge management solutions * Build secure enterprise AI integrations ...
Design Retrieval-Augmented Generation (RAG) architectures, vector databases, prompt engineering frameworks, and enterprise knowledge management solutions * Build secure enterprise AI integrations ...
Familiar with RAG (Retrieval-Augmented Generation) pipelines, vector databases, or orchestration frameworks. * Capable of working with GraphQL, microservices, or event-driven systems in fast-paced ...
Familiar with RAG (Retrieval-Augmented Generation) pipelines, vector databases, or orchestration frameworks. * Capable of working with GraphQL, microservices, or event-driven systems in fast-paced ...
Deep understanding of LLMs, RAG architectures, vector databases, and agentic AI frameworks (e.g., LangChain, AutoGen). * Familiarity with responsible AI practices, model explainability, and human ...
Quick apply
Deep understanding of LLMs, RAG architectures, vector databases, and agentic AI frameworks (e.g., LangChain, AutoGen). * Familiarity with responsible AI practices, model explainability, and human ...
Implement efficient retrieval architectures using vector databases and hybrid search approaches. Develop data preprocessing pipelines that clean and enrich data for AI consumption. Establish data ...
Implement efficient retrieval architectures using vector databases and hybrid search approaches. Develop data preprocessing pipelines that clean and enrich data for AI consumption. Establish data ...
Implement efficient retrieval architectures using vector databases and hybrid search approaches. Develop data preprocessing pipelines that clean and enrich data for AI consumption. Establish data ...
Implement efficient retrieval architectures using vector databases and hybrid search approaches. Develop data preprocessing pipelines that clean and enrich data for AI consumption. Establish data ...
Implement efficient retrieval architectures using vector databases and hybrid search approaches. Develop data preprocessing pipelines that clean and enrich data for AI consumption. Establish data ...
Implement efficient retrieval architectures using vector databases and hybrid search approaches. Develop data preprocessing pipelines that clean and enrich data for AI consumption. Establish data ...
Deep understanding of LLMs, RAG architectures, vector databases, and agentic AI frameworks (e.g., LangChain, AutoGen). * Familiarity with responsible AI practices, model explainability, and human ...
Quick apply
Deep understanding of LLMs, RAG architectures, vector databases, and agentic AI frameworks (e.g., LangChain, AutoGen). * Familiarity with responsible AI practices, model explainability, and human ...
Deep understanding of LLMs, RAG architectures, vector databases, and agentic AI frameworks (e.g., LangChain, AutoGen). * Familiarity with responsible AI practices, model explainability, and human ...
Deep understanding of LLMs, RAG architectures, vector databases, and agentic AI frameworks (e.g., LangChain, AutoGen). * Familiarity with responsible AI practices, model explainability, and human ...
Deep understanding of LLMs, RAG architectures, vector databases, and agentic AI frameworks (e.g., LangChain, AutoGen). * Familiarity with responsible AI practices, model explainability, and human ...
Deep understanding of LLMs, RAG architectures, vector databases, and agentic AI frameworks (e.g., LangChain, AutoGen). * Familiarity with responsible AI practices, model explainability, and human ...
Deep understanding of LLMs, RAG architectures, vector databases, and agentic AI frameworks (e.g., LangChain, AutoGen). * Familiarity with responsible AI practices, model explainability, and human ...
Deep understanding of LLMs, RAG architectures, vector databases, and agentic AI frameworks (e.g., LangChain, AutoGen). * Familiarity with responsible AI practices, model explainability, and human ...
Deep understanding of LLMs, RAG architectures, vector databases, and agentic AI frameworks (e.g., LangChain, AutoGen). * Familiarity with responsible AI practices, model explainability, and human ...
Deep understanding of LLMs, RAG architectures, vector databases, and agentic AI frameworks (e.g., LangChain, AutoGen). * Familiarity with responsible AI practices, model explainability, and human ...
ERP AI Engineer - Manager
Louisville, KY · On-site
$99K - $232K/yr
... with vector databases and semantic search architectures - Translating complex business problems into AI solution designs - Contributing to business development and proposal writing - Cloud ...
ERP AI Engineer - Manager
Louisville, KY · On-site
$99K - $232K/yr
... with vector databases and semantic search architectures - Translating complex business problems into AI solution designs - Contributing to business development and proposal writing - Cloud ...
Experience with vector databases (e.g., Milvus, Pinecone, Chroma, FAISS or similar) and embedding-based retrieval. Experience with GenAI model build: training, fine-tuning, and validation; practical ...
Experience with vector databases (e.g., Milvus, Pinecone, Chroma, FAISS or similar) and embedding-based retrieval. Experience with GenAI model build: training, fine-tuning, and validation; practical ...
Vector Databases information
What are vector databases?
Vector databases are specialized databases designed to store, manage, and search high-dimensional vector data, which is commonly generated from machine learning models, such as embeddings from natural language processing or image recognition. They enable efficient similarity search operations, such as finding the most similar items to a given query vector, which is essential for applications like recommendation systems, semantic search, and AI-powered search engines. Unlike traditional databases that handle structured or unstructured data, vector databases are optimized for fast and scalable similarity searches on large datasets of vectors.
What are some common challenges faced when working with vector databases, and how can they be addressed?
Professionals working with vector databases often encounter challenges such as efficiently scaling to handle large datasets, ensuring low-latency similarity searches, and integrating the database with machine learning pipelines. To address these, teams typically implement distributed architectures, fine-tune indexing strategies, and collaborate closely with data engineers and machine learning specialists. Staying updated with the latest developments in vector database technologies and maintaining clear communication with cross-functional teams are also key to overcoming these challenges.
What is the difference between Vector Databases vs Data Engineers?
| Aspect | Vector Databases | Data Engineers |
|---|---|---|
| Required Skills | Database management, data modeling, query optimization | Data pipeline development, ETL processes, programming |
| Work Environment | Data storage systems, AI/ML projects, cloud platforms | Data infrastructure, cloud environments, big data tools |
| Industry Usage | AI, machine learning, recommendation systems | Data integration, analytics, data architecture |
While Vector Databases focus on storing and querying high-dimensional vector data for AI applications, Data Engineers build and maintain data pipelines and infrastructure to support data analysis and machine learning workflows. Both roles are essential in data-driven industries but serve different functions within the data ecosystem.
What are the key skills and qualifications needed to thrive as a Vector Database Engineer, and why are they important?
Success as a Vector Database Engineer requires a strong background in computer science, database management, and experience with machine learning or AI-driven data systems. Familiarity with vector database platforms (such as Pinecone, Milvus, or Weaviate), cloud infrastructure, and proficiency in languages like Python are typically expected. Strong problem-solving skills, effective communication, and the ability to work cross-functionally help engineers stand out. These competencies are vital to efficiently design, deploy, and maintain scalable vector search solutions that power modern AI applications.
What are popular job titles related to Vector Databases jobs in Kentucky? For Vector Databases jobs in Kentucky, the most frequently searched job titles are:
What job categories do people searching Vector Databases jobs in Kentucky look for? The top searched job categories for Vector Databases jobs in Kentucky are:
What cities in Kentucky are hiring for Vector Databases jobs? Cities in Kentucky with the most Vector Databases job openings:
$218K/yr
Full-time
Posted 28 days ago
BrightSpring Health Services rating
4.6
Based on 60 frontline employees who took The Breakroom Quiz
213th of 228 rated social care providers
Job description
Overview
We are seeking a highly experienced and hands-on Principal Enterprise Architect to lead the full stack design and integration of advanced AI/ML platform and solution architectures within our AI-enabled Health Cloud Platform. This role combines deep expertise in end to end systems architecture, platform engineering, and integration/API design, enabling seamless, secure, and scalable AI/ML healthcare applications.
You will play a critical role in shaping both the technical foundation of the platform and the delivery of intelligent healthcare solutions, ensuring that AI capabilities such as Generative AI, Agentic AI, RPA, and fine-tuned RAG/Vector DB models are effectively embedded into clinical and pharmacy workflows.
Responsibilities
- Architect and lead the full stack implementation of end-to-end AI/ML platform and solution architectures, ensuring seamless integration with enterprise systems and healthcare data sources.
- Design and develop robust, scalable APIs and microservices using technologies such as .NET, C#, and RESTful services.
- Define and enforce platform and integration architecture standards, including data contracts, API security, service orchestration, and interoperability.
- Collaborate with AI/ML engineers, product managers, API, and data engineers to translate business and clinical requirements into cloud-native, reusable platform capabilities and solution-specific workflows.
- Architect and optimize LLM-based systems, including RAG pipelines, vector databases, and agentic AI frameworks (e.g., LangChain, AutoGen).
- Design and evolve the AI/ML platform architecture, including model lifecycle management, orchestration layers, and reusable AI services.
- Ensure all solutions and platform components are HIPAA-compliant, secure, and aligned with healthcare interoperability standards (FHIR, HL7 etc.).
- Evaluate and integrate third-party AI services, open-source tools, and cloud-native components into the platform.
- Provide architectural leadership across model training, deployment, monitoring, and retraining, ensuring scalability and performance.
Qualifications
- 10+ years of experience in solution and platform architecture, with a strong focus on AI/ML systems and enterprise integration.
- 15+ years in overall solution architecture.
- Proven experience designing and delivering AI-powered healthcare or pharmacy platforms and solutions.
- Experience with multi-agent systems, RPA tools, and intelligent automation in healthcare.
- Strong experience with API development and integration using .NET, C#, and modern API frameworks.
- Deep understanding of cloud platforms (Azure preferred), containerization (Docker, Kubernetes), and MLOps practices.
- Expertise in Generative AI, RAG architectures, vector databases, and agentic AI orchestration.
- Expertise in healthcare data standards and secure data handling practices.
- Excellent communication and stakeholder engagement skills.
Preferred Qualifications:
- Background in AI/ML engineering, data science, or biomedical informatics.
- Knowledge of responsible AI, model explainability, and bias mitigation.
- Advanced degree (MS or PhD) in Computer Science, AI/ML, or a related field.
What BrightSpring Health Services employees say
Pay
Benefits
Hours and flexibility
Workplace
Get the full story on Breakroom
About BrightSpring Health Services
Sourced by ZipRecruiter
Industry
Health care and social assistance
Company size
10,000+ Employees
Headquarters location
Louisville, KY, US
Year founded
1974