LLM-based application development, retrieval-augmented generation (RAG) architectures, agentic design patterns, prompt engineering, or vector databases • Demonstrated ability to learn new technical ...
LLM-based application development, retrieval-augmented generation (RAG) architectures, agentic design patterns, prompt engineering, or vector databases • Demonstrated ability to learn new technical ...
... test generation, AI-augmented design/ADRs) while staying hands-on in critical code paths and ... retrieval, agentic patterns, evals, and managing latency/cost/reliability tradeoffs. * Proven track ...
Quick apply
... test generation, AI-augmented design/ADRs) while staying hands-on in critical code paths and ... retrieval, agentic patterns, evals, and managing latency/cost/reliability tradeoffs. * Proven track ...
... test generation, AI-augmented design/ADRs) while staying hands-on in critical code paths and ... retrieval, agentic patterns, evals, and managing latency/cost/reliability tradeoffs. * Proven track ...
... test generation, AI-augmented design/ADRs) while staying hands-on in critical code paths and ... retrieval, agentic patterns, evals, and managing latency/cost/reliability tradeoffs. * Proven track ...
... test generation, AI-augmented design/ADRs) while staying hands-on in critical code paths and ... retrieval, agentic patterns, evals, and managing latency/cost/reliability tradeoffs. * Proven track ...
... test generation, AI-augmented design/ADRs) while staying hands-on in critical code paths and ... retrieval, agentic patterns, evals, and managing latency/cost/reliability tradeoffs. * Proven track ...
Retrieval Augmented Generation information
What does a retrieval augmented generation engineer do?
A Retrieval Augmented Generation engineer typically spends their day designing and implementing systems that combine information retrieval with advanced generative models, such as large language models. This includes fine-tuning models, integrating external data sources, developing vector search pipelines, and evaluating output quality. Collaboration with data scientists, machine learning engineers, and product teams is common to ensure the solutions meet user requirements and scale effectively. Additionally, RAG engineers often troubleshoot issues, monitor model performance in production, and stay informed about the latest advancements in AI and information retrieval.
What is a retrieval augmented generation?
A Retrieval Augmented Generation (RAG) job typically involves developing and optimizing AI systems that enhance text generation by incorporating external knowledge retrieved from relevant sources. Professionals in this field work on integrating retrieval mechanisms with large language models to improve the relevance, accuracy, and factual grounding of generated content. Common responsibilities include designing retrieval systems, fine-tuning language models, optimizing performance, and ensuring the seamless integration of factual data into AI-generated text. This role is highly interdisciplinary, involving expertise in natural language processing (NLP), machine learning, and information retrieval.
What skills and qualifications are needed for retrieval augmented generation?
To thrive in a Retrieval Augmented Generation (RAG) engineering role, you need a solid background in machine learning, natural language processing (NLP), and experience with scalable information retrieval systems, typically supported by a relevant degree in computer science or a related field. Familiarity with tools such as Python, PyTorch or TensorFlow, vector databases, and search platforms like Elasticsearch is essential, along with practical experience deploying and tuning RAG pipelines. Strong problem-solving skills, a collaborative mindset, and effective communication abilities set outstanding professionals apart in this field. These competencies are crucial for designing, implementing, and optimizing hybrid retrieval-generation AI systems that address complex, real-world information needs.
What are the most commonly searched types of Retrieval Augmented Generation jobs in Utah? The most popular types of Retrieval Augmented Generation jobs in Utah are:
What are popular job titles related to Retrieval Augmented Generation jobs in Utah? For Retrieval Augmented Generation jobs in Utah, the most frequently searched job titles are:
What job categories do people searching Retrieval Augmented Generation jobs in Utah look for? The top searched job categories for Retrieval Augmented Generation jobs in Utah are:
What cities in Utah are hiring for Retrieval Augmented Generation jobs? Cities in Utah with the most Retrieval Augmented Generation job openings:
Full-time
Re-posted 22 days ago
Job description
About the Role
MGT is hiring AI Solutions Architects to join our AI Operating Group (AI OG). The AI OG is responsible for both internal AI tool development and client-facing AI solution delivery, primarily serving the state and local government market.
This is a hands-on role. You will design and build AI-powered solutions for real client problems, not write slide decks about what AI could do. You will work across the full lifecycle: discovery, architecture, build, deployment, and iteration. The right person for this role sits comfortably at the intersection of technical capability and business problem-solving.
This is not a traditional software engineering position. It is the cross roads of consulting and building. We need people who can sit in a room with a client, understand their operational challenge, and translate that into a working AI architecture. You should be comfortable with concepts like RAG pipelines, agentic workflows, prompt engineering, and cloud deployment. But your real value is in how you think and solve problems, not just what you can code.
What You'll Do
• Design end-to-end AI solution architectures for client engagements, from problem discovery through production deployment
• Build and implement RAG pipelines, agentic workflows, and multi-agent systems using frameworks such as LangChain and LangGraph
• Architect data pipelines and integration patterns that connect AI capabilities to existing client systems and data sources
• Work with tool-layer integration standards such as MCP (Model Context Protocol) to connect agents with enterprise systems
• Develop reusable components, skills, templates, and accelerators that scale across multiple engagements
• Collaborate with project leads, consultants, and subject matter experts to translate business requirements into technical specifications and solution designs
• Support internal product development across MGT's AI tool suite
• Present technical architectures and solution recommendations to both internal leadership and client stakeholders
• Participate in discovery sessions and workshops to identify high-impact AI use cases within client organizations
Required Qualifications
• 3-5 years of professional experience; does not have to be in AI, but must demonstrate strong technical problem-solving ability and a track record of building solutions that work
• Hands-on experience with one or more of the following: LLM-based application development, retrieval-augmented generation (RAG) architectures, agentic design patterns, prompt engineering, or vector databases
• Demonstrated ability to learn new technical capabilities and platforms quickly
• Strong communication skills; you will work with consultants, clients, and executive leadership, not just engineers
• Ability to independently scope, architect, and deliver technical solutions with minimal oversight
• A builder mentality: you would rather figure it out and ship it than wait for a detailed specification
• Bachelor's degree or equivalent practical experience
Preferred Qualifications
• Experience in consulting, professional services, or client-facing technical delivery
• Background in data architecture, ETL/ELT pipelines, or analytics platforms
• Programming experience in Python or similar languages
• Experience working with cloud-based AI services on any major platform
What Success Looks Like
• Within 30 days: You understand our current tool suite, architecture patterns, and active client engagements. You have shipped something.
• Within 90 days: You are independently architecting solutions for client projects and contributing to internal product development.
• Within 6 months: You are leading technical delivery on engagements, mentoring team members on AI solution patterns, and shaping our approach to new use cases.
Why MGT
You will be joining a team that is actively building and shipping AI products, not talking about them. We have real tools in production, real clients using them, and a leadership team that understands both the technology and the business.
This is a high-visibility role with direct access to senior leadership and the opportunity to shape how AI gets delivered across the organization. We are building the AI practice from the ground up, which means you will have an outsized impact on the tools, processes, and culture of the team.
Our philosophy: clean data foundations first, AI layered on top. Process understanding before automation. Empowering domain experts to build, not centralizing AI capability in a silo. If that resonates with you, this is your team.
NOTE: We currently do not accept candidates who require sponsorship, nor are we able to provide sponsorship opportunities to candidates.
Positions are available in Salt Lake City, Utah; Washington, D.C.; and remote. Remote employees will be expected to travel to an office periodically.
MGT is hiring AI Solutions Architects to join our AI Operating Group (AI OG). The AI OG is responsible for both internal AI tool development and client-facing AI solution delivery, primarily serving the state and local government market.
This is a hands-on role. You will design and build AI-powered solutions for real client problems, not write slide decks about what AI could do. You will work across the full lifecycle: discovery, architecture, build, deployment, and iteration. The right person for this role sits comfortably at the intersection of technical capability and business problem-solving.
This is not a traditional software engineering position. It is the cross roads of consulting and building. We need people who can sit in a room with a client, understand their operational challenge, and translate that into a working AI architecture. You should be comfortable with concepts like RAG pipelines, agentic workflows, prompt engineering, and cloud deployment. But your real value is in how you think and solve problems, not just what you can code.
What You'll Do
• Design end-to-end AI solution architectures for client engagements, from problem discovery through production deployment
• Build and implement RAG pipelines, agentic workflows, and multi-agent systems using frameworks such as LangChain and LangGraph
• Architect data pipelines and integration patterns that connect AI capabilities to existing client systems and data sources
• Work with tool-layer integration standards such as MCP (Model Context Protocol) to connect agents with enterprise systems
• Develop reusable components, skills, templates, and accelerators that scale across multiple engagements
• Collaborate with project leads, consultants, and subject matter experts to translate business requirements into technical specifications and solution designs
• Support internal product development across MGT's AI tool suite
• Present technical architectures and solution recommendations to both internal leadership and client stakeholders
• Participate in discovery sessions and workshops to identify high-impact AI use cases within client organizations
Required Qualifications
• 3-5 years of professional experience; does not have to be in AI, but must demonstrate strong technical problem-solving ability and a track record of building solutions that work
• Hands-on experience with one or more of the following: LLM-based application development, retrieval-augmented generation (RAG) architectures, agentic design patterns, prompt engineering, or vector databases
• Demonstrated ability to learn new technical capabilities and platforms quickly
• Strong communication skills; you will work with consultants, clients, and executive leadership, not just engineers
• Ability to independently scope, architect, and deliver technical solutions with minimal oversight
• A builder mentality: you would rather figure it out and ship it than wait for a detailed specification
• Bachelor's degree or equivalent practical experience
Preferred Qualifications
• Experience in consulting, professional services, or client-facing technical delivery
• Background in data architecture, ETL/ELT pipelines, or analytics platforms
• Programming experience in Python or similar languages
• Experience working with cloud-based AI services on any major platform
What Success Looks Like
• Within 30 days: You understand our current tool suite, architecture patterns, and active client engagements. You have shipped something.
• Within 90 days: You are independently architecting solutions for client projects and contributing to internal product development.
• Within 6 months: You are leading technical delivery on engagements, mentoring team members on AI solution patterns, and shaping our approach to new use cases.
Why MGT
You will be joining a team that is actively building and shipping AI products, not talking about them. We have real tools in production, real clients using them, and a leadership team that understands both the technology and the business.
This is a high-visibility role with direct access to senior leadership and the opportunity to shape how AI gets delivered across the organization. We are building the AI practice from the ground up, which means you will have an outsized impact on the tools, processes, and culture of the team.
Our philosophy: clean data foundations first, AI layered on top. Process understanding before automation. Empowering domain experts to build, not centralizing AI capability in a silo. If that resonates with you, this is your team.
NOTE: We currently do not accept candidates who require sponsorship, nor are we able to provide sponsorship opportunities to candidates.
Positions are available in Salt Lake City, Utah; Washington, D.C.; and remote. Remote employees will be expected to travel to an office periodically.
About Cicero Group
Sourced by ZipRecruiter
Industry
Business management consulting
Company size
201 - 500 Employees
Headquarters location
Salt Lake City, UT, US
Year founded
2001