Develop and maintain Retrieval-Augmented Generation (RAG) architectures using vector databases and semantic search technologies * Create, test, and refine prompts, structured outputs, and evaluation ...
Develop and maintain Retrieval-Augmented Generation (RAG) architectures using vector databases and semantic search technologies * Create, test, and refine prompts, structured outputs, and evaluation ...
Sierra.ai Consultant
Dallas, TX · On-site
... Retrieval-Augmented Generation (RAG) pipelines, and Agent SDKs - Skilled in building and deploying AI/LLM systems in production environments - Familiarity with AI agents, including evaluation ...
Quick apply
Sierra.ai Consultant
Dallas, TX · On-site
... Retrieval-Augmented Generation (RAG) pipelines, and Agent SDKs - Skilled in building and deploying AI/LLM systems in production environments - Familiarity with AI agents, including evaluation ...
AI Engineer
Dallas, TX · On-site
Develop and maintain Retrieval-Augmented Generation (RAG) architectures using vector databases and semantic search technologies * Create, test, and refine prompts, structured outputs, and evaluation ...
AI Engineer
Dallas, TX · On-site
Develop and maintain Retrieval-Augmented Generation (RAG) architectures using vector databases and semantic search technologies * Create, test, and refine prompts, structured outputs, and evaluation ...
AI Engineer
Dallas, TX · On-site
Develop and maintain Retrieval-Augmented Generation (RAG) architectures using vector databases and semantic search technologies * Create, test, and refine prompts, structured outputs, and evaluation ...
Quick apply
AI Engineer
Dallas, TX · On-site
Develop and maintain Retrieval-Augmented Generation (RAG) architectures using vector databases and semantic search technologies * Create, test, and refine prompts, structured outputs, and evaluation ...
In this role, you will design, build, and enhance intelligent applications thatleverageLarge Language Models (LLMs), document processing pipelines, Retrieval-Augmented Generation (RAG) architectures ...
In this role, you will design, build, and enhance intelligent applications thatleverageLarge Language Models (LLMs), document processing pipelines, Retrieval-Augmented Generation (RAG) architectures ...
Engineer robust Retrieval-Augmented Generation (RAG) solutions that aggregate diverse business intelligence-spanning strategic client priorities, communication history, and value metrics-to ensure ...
Engineer robust Retrieval-Augmented Generation (RAG) solutions that aggregate diverse business intelligence-spanning strategic client priorities, communication history, and value metrics-to ensure ...
Engineer robust Retrieval-Augmented Generation (RAG) solutions that aggregate diverse business intelligence-spanning strategic client priorities, communication history, and value metrics-to ensure ...
Engineer robust Retrieval-Augmented Generation (RAG) solutions that aggregate diverse business intelligence-spanning strategic client priorities, communication history, and value metrics-to ensure ...
Python Developer with LLM, GCP
Irving, TX · On-site
$48 - $66.25/hr
Advanced expertise in Prompt Engineering, fine-tuning, and Retrieval-Augmented Generation (RAG) techniques. Experience working with Vector databases and text embeddings. Experience within Google ...
Quick apply
Python Developer with LLM, GCP
Irving, TX · On-site
$48 - $66.25/hr
Advanced expertise in Prompt Engineering, fine-tuning, and Retrieval-Augmented Generation (RAG) techniques. Experience working with Vector databases and text embeddings. Experience within Google ...
Configure and optimize Retrieval-Augmented Generation (RAG) architectures, integrating both structured and unstructured data sources into unified vector engines. * Manage LLM integration challenges ...
Configure and optimize Retrieval-Augmented Generation (RAG) architectures, integrating both structured and unstructured data sources into unified vector engines. * Manage LLM integration challenges ...
GenAI Context Engineer
Dallas, TX · On-site
Design and implement enterprise Retrieval Augmented Generation (RAG) architectures for GenAI platforms and applications. * Build and optimize semantic retrieval pipelines, vector search ...
GenAI Context Engineer
Dallas, TX · On-site
Design and implement enterprise Retrieval Augmented Generation (RAG) architectures for GenAI platforms and applications. * Build and optimize semantic retrieval pipelines, vector search ...
Machine Learning Engineer
Frisco, TX · On-site
Architect Retrieval-Augmented Generation ( RAG ) systems, including vector store design, hybrid search strategies, chunking pipelines, and context relevance evaluation. * Apply MLOps best practices ...
Machine Learning Engineer
Frisco, TX · On-site
Architect Retrieval-Augmented Generation ( RAG ) systems, including vector store design, hybrid search strategies, chunking pipelines, and context relevance evaluation. * Apply MLOps best practices ...
Python Developer with ML - Dallas, TX
$49.75 - $68.50/hr
Develop and optimize Retrieval-Augmented Generation (RAG) pipelines for Large Language Models (LLMs) to provide contextually relevant and accurate outputs. This includes ingesting, processing, and ...
Python Developer with ML - Dallas, TX
$49.75 - $68.50/hr
Develop and optimize Retrieval-Augmented Generation (RAG) pipelines for Large Language Models (LLMs) to provide contextually relevant and accurate outputs. This includes ingesting, processing, and ...
Software Engineer - Advanced
Plano, TX · On-site
$90 - $95/hr
You will play a key role in building scalable systems that leverage retrieval-augmented generation (RAG), conversational AI, and cloud-native architectures . Minimum Qualifications * 10+ years of ...
Software Engineer - Advanced
Plano, TX · On-site
$90 - $95/hr
You will play a key role in building scalable systems that leverage retrieval-augmented generation (RAG), conversational AI, and cloud-native architectures . Minimum Qualifications * 10+ years of ...
Built scalable Retrieval-Augmented Generation (RAG) pipelines using vector databases and embedding models. * Designed AI agents with tool calling , function execution , and secure workflow ...
New
Built scalable Retrieval-Augmented Generation (RAG) pipelines using vector databases and embedding models. * Designed AI agents with tool calling , function execution , and secure workflow ...
New
GenAI Ops Solution Architect
Dallas, TX · On-site
$62.50 - $82.50/hr
... Retrieval Augmented Generation (RAG), Agentic AI, ModelOps, Evaluation, Observability, and AI Governance. Future duties and responsibilities · Enterprise GenAI Architecture · Define and govern the ...
GenAI Ops Solution Architect
Dallas, TX · On-site
$62.50 - $82.50/hr
... Retrieval Augmented Generation (RAG), Agentic AI, ModelOps, Evaluation, Observability, and AI Governance. Future duties and responsibilities · Enterprise GenAI Architecture · Define and govern the ...
Python Developer with ML - Dallas, TX
Dallas, TX · On-site
$49.75 - $68.50/hr
OOP, design patterns, modular architecture. • Develop and optimize Retrieval-Augmented Generation (RAG) pipelines for Large Language Models (LLMs) to provide contextually relevant and accurate ...
Python Developer with ML - Dallas, TX
Dallas, TX · On-site
$49.75 - $68.50/hr
OOP, design patterns, modular architecture. • Develop and optimize Retrieval-Augmented Generation (RAG) pipelines for Large Language Models (LLMs) to provide contextually relevant and accurate ...
Retrieval-Augmented Generation (RAG) pipelines and vector databases (e.g., Pinecone, FAISS) * API development and integration (FastAPI, REST, microservices) * Cloud platforms: AWS / Azure / GCP ...
Retrieval-Augmented Generation (RAG) pipelines and vector databases (e.g., Pinecone, FAISS) * API development and integration (FastAPI, REST, microservices) * Cloud platforms: AWS / Azure / GCP ...
AI/ML Engineer
Plano, TX · On-site
Apply retrieval augmented generation (RAG) techniques to data to populate and query vector databases (e.g. Weaviate) * Build custom applications with LLM frameworks such as LangChain, DSPy ...
AI/ML Engineer
Plano, TX · On-site
Apply retrieval augmented generation (RAG) techniques to data to populate and query vector databases (e.g. Weaviate) * Build custom applications with LLM frameworks such as LangChain, DSPy ...
Apply retrieval augmented generation (RAG) techniques to data to populate and query vector databases (e.g. Weaviate) * Build custom applications with LLM frameworks such as LangChain, DSPy ...
Quick apply
Apply retrieval augmented generation (RAG) techniques to data to populate and query vector databases (e.g. Weaviate) * Build custom applications with LLM frameworks such as LangChain, DSPy ...
Apply retrieval augmented generation (RAG) techniques to data to populate and query vector databases (e.g. Weaviate) * Build custom applications with LLM frameworks such as LangChain, DSPy ...
Apply retrieval augmented generation (RAG) techniques to data to populate and query vector databases (e.g. Weaviate) * Build custom applications with LLM frameworks such as LangChain, DSPy ...
Retrieval Augmented Generation Rag information
See Dallas, TX salary details
$14.98 - $16.02
6% of jobs
$16.97 is the 25th percentile. Wages below this are outliers.
$16.02 - $17.06
20% of jobs
$17.06 - $18.09
13% of jobs
The median wage is $18.84 / hr.
$18.09 - $19.13
15% of jobs
$19.13 - $20.17
13% of jobs
$20.73 is the 75th percentile. Wages above this are outliers.
$20.17 - $21.21
15% of jobs
$21.21 - $22.24
3% of jobs
$22.24 - $23.28
2% of jobs
$23.28 - $24.32
4% of jobs
$24.32 - $25.36
7% of jobs
$25.36 - $26.40
1% of jobs
$14
$20
$26
How much do retrieval augmented generation rag jobs pay per hour?

Full-time
Medical, Dental, Vision, Retirement
Posted 19 days ago
Job description
Ready to Apply?
Pereview Software is seeking an AI Engineer to join our growing Product and Engineering team. This is a unique opportunity to help shape the future of AI-powered solutions within the commercial real estate industry.
In this role, you will design, build, and enhance intelligent applications that leverage Large Language Models (LLMs), document processing pipelines, Retrieval-Augmented Generation (RAG) architectures, and Azure AI technologies. You will work closely with our engineering, product, and leadership teams to transform complex real estate and financial data into actionable insights and automation solutions.
If you're passionate about applying AI to real-world business problems, enjoy building scalable solutions, and want to help drive the next generation of innovation at Pereview, we'd love to meet you.
Please complete this brief survey: https://go.cultureindex.com/p/niy2xbmLp8t8rect6dx
What You'll Be Doing
- Design, develop, and maintain AI-powered applications and services within the Pereview platform
- Take ownership of existing AI solutions and enhance their scalability, performance, and accuracy
- Build and optimize document ingestion, OCR, and data extraction workflows for financial and real estate documents
- Develop and maintain Retrieval-Augmented Generation (RAG) architectures using vector databases and semantic search technologies
- Create, test, and refine prompts, structured outputs, and evaluation frameworks for Large Language Models
- Integrate OpenAI and Azure OpenAI services into production applications
- Develop APIs, backend services, and data pipelines supporting AI initiatives
- Collaborate with product managers, engineers, and business stakeholders to identify opportunities for AI-driven innovation
- Monitor, troubleshoot, and continuously improve AI model performance and system reliability
- Participate in architectural planning and contribute to the long-term AI strategy of the organization
Requirements
- 3+ years of software development experience with Python and modern application development
- Experience building AI/ML solutions using OpenAI APIs and/or Azure OpenAI Services
- Experience developing Retrieval-Augmented Generation (RAG) solutions, including embeddings, chunking, vector search, and document retrieval
- Experience building document processing and extraction pipelines, including PDF parsing, OCR, and structured data extraction
- Strong understanding of prompt engineering, prompt evaluation, and structured output validation
- Experience with LLM orchestration frameworks such as LangChain, Semantic Kernel, or similar technologies
- Experience working with JSON, structured outputs, and data validation
- Experience building data ingestion and transformation workflows
Preferred Qualifications
- Experience working with document-heavy industries such as commercial real estate, financial services, lending, legal, or accounting
- Experience processing mortgage statements, financial reports, legal documents, or similar unstructured data sources
- Experience with Azure AI services and cloud-based AI deployments
- Experience extending, maintaining, or scaling production AI solutions
WHO ARE WE?
Pereview Software is the fastest growing provider of asset and portfolio management software to the global commercial real estate industry. To that end, multiple times since our inception, we have been recognized by Inc. 500, Dallas 100 as a fastest growing privately held business in the United States and have also been recognized by the Dallas Business Journal as one of the top places to work.
Pereview Software is the only life of the asset solution to the commercial investment management industry supporting both debt and equity investments. We serve clients on a global basis from very small investment management managers to some of the largest global firms in the industry.
Benefits
WHAT'S IN IT FOR YOU?
- Health, Vision, and Dental benefits to fit your needs
- 401k-4% Company match
- Discretionary Time Off-3 weeks off annually
LOCATION
- To be considered for this position, applicants must live in Dallas, TX.
- Ability to work in office Monday-Friday: 12400 Coit Rd. Ste 570 Dallas, TX 75251
- *We are not sponsoring H1B or OPT candidates*
Please complete this brief survey: https://go.cultureindex.com/p/niy2xbmLp8t8rect6dx
About Pereview Software
Sourced by ZipRecruiter
Industry
Real estate
Company size
1 - 10 Employees
Headquarters location
Dallas, TX, US
Year founded
2011