1

Ai Rag Jobs in Kentucky (NOW HIRING)

$150 - $200/hr

Integrate AI capabilities (LLM APIs, intelligent automation, personalization) into our ASP.NET MVC ... Implement complex RAG pipelines andoptimizetrade-offs between massive-context hydration and multi ...

$150 - $200/hr

RAG-based internal knowledge solutions * Shared SDKs, templates, and integration examples * Reusable components for copilots, agents, and AI-enabled engineering workflows * Partner with senior ...

New

$150 - $200/hr

The Data & AI Engineer will implement retrieval‑augmented generation (RAG) patterns, embedding and indexing pipelines, vector stores, and semantic models alongside core ELT, streaming, and ...

$150 - $200/hr

Deep working knowledge of modern AI capabilities (LLMs, agents, custom inference, RAG) * Proven ability to communicate technical concepts to non-technical executives * Experience leading multi ...

$200 - $250/hr

Worth AI is hiring a Senior Agentic AI Engineer to design and ship production agent systems that ... Strong RAG fundamentals chunking, embeddings, hybrid retrieval, reranking, grounding - and judgment ...

$200 - $250/hr

Modern AI Fluency: Familiarity with GenAI, agentic AI, RAG, ML/LLMOps, model evaluation, model serving, and governed AI patterns. Experience with Databricks Mosaic AI, Agent Bricks, MLflow, or Vector ...

$150 - $200/hr

Build and operate production AI services: agent runtimes, RAG pipelines, custom inference endpoints * Optimize latency, throughput, and cost across the model serving stack * Implement evaluation ...

$125 - $150/hr

About the Role Join our engineering team at the forefront of applied AI to design and build ... Build and optimize retrieval-augmented generation (RAG) pipelines including document ingestion ...

$150 - $200/hr

Red-team LLM-powered systems: chatbots, copilots, RAG pipelines, AI agents, tool-calling workflows, and API-based AI products. * Test for jailbreaks, prompt injection, system-prompt and tool leakage ...

$150 - $200/hr

Forward Deployed AI Engineer/Anthropic - Data Intelligence-US East Directly uses Claude/Anthropic and RAG workflows; building LLM apps, connectors, and agentic AI - practical AI dev work with rapid ...

$200 - $250/hr

As an AI Architect, You will design and build agentic AI systems across multiple Industries You ... Design and implement Knowledge Graph and Graph RAG architectures to improve reasoning, contextual ...

$150 - $200/hr

Deep working knowledge of modern AI architectures (agents, RAG, custom inference, fine-tuning) * Strong cloud architecture skills across at least one major provider * Demonstrated ability to lead ...

$80 - $100/hr

AI Software Engineering/Research Internship (unpaid) Location: Remote (U.S. based preferred) Type ... LLMs, Agents, RAG, MCP, and Prompt Engineering). * Exceptional core CS skills related to data ...

$80 - $100/hr

AI Software Engineering/Research Internship (unpaid) Location: Remote (U.S. based preferred) Type ... LLMs, Agents, RAG, MCP, and Prompt Engineering). * Exceptional core CS skills related to data ...

$125 - $150/hr

RAG architectures * Embeddings * Semantic search * Re-ranking * Prompt engineering * Vector ... AI governance * Security and privacy requirements * Model validation * Access controls

New

$125 - $150/hr

This role focuses on developing LLM‑powered applications, RAG systems, intelligent agents, and full‑stack AI workflows--from prototype through production. You will translate business needs into ...

$150 - $200/hr

Large Language Models (LLMs) Retrieval-Augmented Generation (RAG) architectures Prompt engineering techniques Agentic AI workflows and orchestration Build intelligent systems using frameworks such as ...

$125 - $150/hr

Hands-on experience designing and delivering enterprise AI/ML solutions, including RAG architectures, agent orchestration, conversational AI, knowledge retrieval, and integration protocols such as ...

$150 - $200/hr

Design and build systems involving knowledge graphs, ontologies, graph and vector databases, RAG, and related AI-enabled application functionality. * Design and implement scalable agentic pipelines ...

$150 - $200/hr

Build and maintain RAG pipelines and integrations with multiple LLM providers (Gemini, GPT, Claude ... Experience building and reasoning about multi-agent AI systems and agentic workflows * Solid ...

Showing results 41-60

Ai Rag information

What is an AI RAG?

AI RAGs, or Retrieval-Augmented Generation systems, are a type of artificial intelligence that combines the power of retrieving information from large databases or documents with generating human-like text responses. This approach allows AI models to provide more accurate, up-to-date, and contextually relevant answers by referencing external data sources during the generation process. RAGs are commonly used in applications like chatbots, search engines, and customer support systems, where comprehensive and factual responses are important.

What are the key skills and qualifications needed to thrive as an AI researcher?

To thrive as an AI Researcher, you need a strong background in computer science, mathematics, and machine learning, usually with an advanced degree such as a Master's or Ph.D. Proficiency with programming languages like Python, deep learning frameworks (e.g., TensorFlow, PyTorch), and familiarity with scientific research tools is essential. Critical thinking, creativity, and effective collaboration are vital soft skills for generating novel ideas and working in multidisciplinary teams. These skills and qualities are crucial to drive innovation and solve complex problems in the rapidly evolving field of artificial intelligence.

What are common challenges faced by AI RAG engineers when integrating retrieval systems with large language models?

AI RAG engineers often encounter challenges such as ensuring seamless integration between retrieval systems and language models, maintaining low latency for real-time responses, and handling the quality and relevance of retrieved data. Additionally, tuning the system to balance retrieval accuracy with generative fluency can be complex, especially when dealing with large or unstructured datasets. Collaboration with data engineers, ML researchers, and product teams is essential to address these challenges and optimize system performance.

What is the difference between Ai Rag vs Data Analyst?

AspectAi RagData Analyst
Required CredentialsTypically a diploma or certification in AI, machine learning, or related fieldsBachelor's degree in statistics, mathematics, or related fields
Work EnvironmentTech companies, AI startups, research labsBusiness, finance, healthcare, and various industries
Employer & Industry UsagePrimarily in AI development and researchAcross industries for data interpretation and decision-making
Common Search & ComparisonYesYes

Ai Rag and Data Analyst roles share overlapping skills in data handling and analysis, but Ai Rag focuses more on AI-specific applications and machine learning, while Data Analysts concentrate on interpreting data to inform business decisions. Both roles are vital in data-driven industries, with Ai Rag often working in AI development environments and Data Analysts supporting strategic insights across sectors.

What are popular job titles related to Ai Rag jobs in Kentucky?

For Ai Rag jobs in Kentucky, the most frequently searched job titles are:

What cities in Kentucky are hiring for Ai Rag jobs?

Cities in Kentucky with the most Ai Rag job openings:

Infographic showing various Ai Rag job openings in Kentucky as of September 2026, with employment types broken down into 50% Full Time, and 50% Contract. Highlights an 100% In-person job distribution.

$150 - $200/hr

Other

Posted 10 days ago


Key responsibilities

  • Integrate AI capabilities such as LLM APIs, automation, and personalization into ASP.NET MVC products.

  • Design, develop, and deploy secure, scalable AI systems and microservices, including enterprise LLM integration and multi-agent workflows.

  • Identify modernization opportunities, migrate legacy features to AI-native architectures, and develop CI/CD pipelines with AI-driven testing and red-teaming.


Job description

About Us

At Pinpoint Global, we build training and compliance platforms that organizations rely on to keep their teams skilled, certified, andaudit-ready.We'repart of theValsoftEdelweiss Software Group — a large-scale portfolio of vertical market B2B SaaS companies — and weoperatewith a startup mindset: high ownership, high velocity, and real ROI.

Our core stack is ASP.NET MVC + MS SQL — battle-tested and ready to evolve.We'relooking for true builders: engineers who orchestrate systems, ship production-grade AI, and modernize massive legacy codebases at speed.

The Role

You'llembed directly in our engineering team, working hands-on inside our .NET codebase and broader product suite. Your mission is to act as an organizational force multiplier — turning legacy inefficiencies into intelligent systems, increasing Net Revenue Retention (NRR), and driving measurable business impact through production-grade AI.

This is a full-stack role with direct product impact. If you enjoy owning problems end-to-end, have a relentless bias toward action, and thrive on shipping real systems at high velocity — this role is for you.

What You'll DoBuild & Ship AI Systems
  • Integrate AI capabilities (LLM APIs, intelligent automation, personalization) into our ASP.NET MVC products
  • Design, develop, and deploy production-grade, secure AI systems using scalable polyglot microservices
  • Integrate enterprise LLMs (Anthropic Claude, OpenAI, Google Gemini) into SaaS platforms via fault-tolerant API routing gateways
  • Develop autonomous multi-agent workflows using parallel orchestration tools (Claude Code CLI, OpenAI Codex)
  • Build new product surfaces — smart content recommendations, automated compliance tracking, AI-assisted reporting
  • Rapidly prototype →validatevia adversarial testing → deploy → iterate
Architect AI Infrastructure
  • Implement complex RAG pipelines andoptimizetrade-offs between massive-context hydration and multi-stage semantic retrieval
  • Build vector databases (Pinecone,Weaviate, FAISS) and manage persistent document embedding queues
  • Build polyglot microservices handling long-running tasks and streaming viaWebSocketsand Server-Sent Events
  • Ensure SOC 2 compliance, data residency controls, and deterministic execution through policy-as-code agentic governance
  • Deploy and scale models within secure managed cloud boundaries
Modernize& Collaborate
  • Identifyhigh-impact modernization opportunities across our training and compliance platform
  • Help migrate legacy features into scalable, AI-native architectures using agentic swarm coding and automated refactoring
  • Architect zero-touch CI/CD pipelines with adversarial gating and AI-driven test automation
  • Integrate synthetic red teaming into CI/CD to prevent prompt drift, reward hacking, and logic degradation
  • Work directly with non-technical stakeholders to translate ambiguous business problems into secure, scalable AI solutions
  • Collaborate with product and design to ship features end-to-end
Required Technical SkillsCore Engineering
  • 3–5+ years of enterprise software development experience with strong full-stack web fundamentals
  • Hands-on experience with .NET / ASP.NET MVC (our core stack) and C#
  • Fluency across popular languages and frameworks: Python, JavaScript, TypeScript, .NET,NextJS
  • Solid understanding of relational databases — MS SQL experience a plus
  • Backend experience designing polyglot APIs, decoupled async microservices, and persistent connection protocols (WebSockets/SSE)
  • Familiarity with containerization (Docker, Kubernetes) and multi-region cloud infrastructure (AWS, Azure, or GCP)
AI & ML Systems
  • Practical experience integrating AI/ML APIs or building AI-powered features in production
  • Enterprise LLM integration and dynamic API routing (OpenAI, Anthropic, Gemini)
  • Multi-agent orchestration and advanced CLI tooling (Claude Code, OpenAI Codex)
  • Mastery of AI IDE tooling: Cursor for repo-wide reasoning, GitHub Copilot
  • RAG pipeline design: dynamic chunking, vector databases, embedding management
  • Custom evaluations (LangSmith), structured outputs, and managed fine-tuning in secure cloud environments
MLOps& Process Automation
  • Zero-touch CI/CD pipelines and advanced Git workflows (includingworktreeisolation for autonomous sub-agents)
  • Unit test and benchmark automation integrated with AI-driven testing frameworks
  • Adversarial LLM testing and automated synthetic red-teaming
  • Hallucination mitigation, enterprise guardrails, and deterministic policy-as-code execution
  • Real-time token/credit consumption tracking and dynamic access limit monitoring
Bonus Points
  • Experience with prompt engineering, RAG pipelines, or agentic workflows
  • Familiarity with refactoring or re-architecting legacy .NET applications
  • Background in regulated industries: HR tech, e-learning, compliance, LMS platforms
  • Knowledge of SOC 2 audit requirements and compliance automation tooling
Who You Are
  • Highly hands-on — you ship, not just design; youoperateat velocity by orchestrating autonomous tools
  • Entrepreneurial startup mindset — you spot legacy inefficiencies and act with a bias toward rapid action
  • Comfortable with ambiguity — you scope, own, and deliver independently
  • Business-oriented —you care about ROI, operational leverage, and financial metrics like NRR and CAC
  • Strong product instincts — you think about the user, not just the implementation
  • Fast learner — you track real-time shifts in AI ecosystems, APIs, and infrastructure
  • Pragmatic — you use the right secure enterprise tool for the bottleneck, not just the flashiest one
Tech Stack

ASP.NET MVC · C# · MS SQL · Python · TypeScript · LLM APIs (Anthropic, OpenAI, Gemini) · RAG / Vector DBs · Docker · Kubernetes · Azure / AWS / GCP · REST APIs ·WebSockets· HTML/CSS/JS

Why Join
  • Shape the AI strategy of a growing compliance and training platform
  • Own meaningful features from day one — not just tickets in a backlog
  • Real modernization challenge: legacy codebase + greenfield AI opportunity in parallel
  • Collaborative, low-ego team that ships and iterates fast
  • Startup velocity inside an established, well-resourced corporate portfolio
#J-18808-Ljbffr