GenAI Engineer (LLM Applications & RAG Architecture) - Q3-2026

R2 Technologies Corporation

$120K — $145K *
Information Technology
Less than 5 years of experience
Job Overview by Ladders

Qualifications

  • 3 years of experience in software engineering, AI/ML, or applied LLM development.
  • Advanced programming skills in Python; experience in Node.js, Java, or TypeScript is a plus.
  • Hands-on expertise with Amazon Bedrock, Azure OpenAI, or direct integration with LLM APIs.
  • Proven experience designing RAG architectures using vector databases like Pinecone or FAISS.
  • Strong knowledge of embeddings, prompt engineering, and model evaluation techniques.
  • Experience building REST APIs and microservices, proficient in SQL and NoSQL databases.

Responsibilities

  • Design and develop production LLM applications, including chatbots and summarization workflows.
  • Build end-to-end RAG pipelines involving document ingestion and hybrid retrieval strategies.
  • Develop and optimize prompt engineering workflows and orchestration layers across model providers.
  • Integrate models via Amazon Bedrock and Azure OpenAI, optimizing for cost and latency.
  • Create scalable Python backend services and REST APIs for enterprise application use.
  • Evaluate model output quality through structured testing and response benchmarking.
Full Job Description
Overview:

Job Summary: Most enterprises have proven that LLMs work in a demo-far fewer have gotten them into production. R2 Technologies is seeking a GenAI Engineer to close that gap. You will design and build LLM-powered applications on enterprise data: document ingestion and structured extraction pipelines, retrieval-augmented generation architectures, prompt and orchestration layers, and the backend services that expose them to business users. This role supports client engagements across financial services, healthcare, and retail, as well as our internal SmartEnt platform.

Key Responsibilities:

  • Design and develop production LLM applications, including chatbots, copilots, document intelligence, and summarization workflows.
  • Build end-to-end RAG pipelines covering document ingestion, chunking strategy, embedding generation, hybrid retrieval, and response grounding.
  • Develop and optimize prompt engineering workflows and LLM service orchestration layers across multiple model providers.
  • Integrate foundation models through Amazon Bedrock, Azure OpenAI, and direct LLM APIs, with routing logic for cost and latency optimization.
  • Build scalable Python backend services and REST APIs that expose GenAI capabilities to enterprise applications.
  • Evaluate model output quality through structured testing, hallucination detection, and response benchmarking against gold datasets.


Qualifications:

  • 3 years of experience in software engineering, AI/ML, or applied LLM development.
  • Advanced programming skills in Python, with additional experience in Node.js, Java, or TypeScript.
  • Hands-on expertise with Amazon Bedrock, Azure OpenAI, or direct integration with LLM APIs and model services.
  • Proven experience designing RAG architectures using vector databases such as Pinecone, Weaviate, ChromaDB, FAISS, or Azure AI Search.
  • Strong knowledge of embeddings, prompt engineering, chunking strategies, and model evaluation techniques.
  • Experience building REST APIs and microservices, with working knowledge of SQL and NoSQL databases and cloud deployment on AWS, Azure, or GCP.


Skills:

NODE.JS,PYTHON,AZURE,JAVA,AI,DATABASES,NOSQL,SQL,TYPESCRIPT,AWS

Similar Jobs

More Jobs at R2 Technologies Corporation

More Information Technology Jobs

Find similar GenAI Engineer (LLM Applications & RAG Architecture) - Q3-2026 jobs: