
RAG Architect
Há 3 dias
Join to apply for the RAG Architect role at Perform
We are seeking a Senior AI Engineer to lead the design and implementation of an end-to-end Retrieval-Augmented Generation (RAG) architecture. This role will drive the ingestion of GitHub repositories, Confluence pages, Qtest artifacts, PRDs, and script libraries to power autoscripting, onboarding search, and long-term knowledge reuse. As a technical leader, you will set the strategic direction, select cutting-edge models, and mentor AI and Automation Agent Engineers to deliver a scalable, secure, and innovative platform.
Key Responsibilities- Architect ingestion and retrieval layers, selecting loaders, chunking strategies (AST-aware for Java), embeddings (e.g., BGE-Code, mxbai), vector stores (e.g., Chroma), cross-encoder rerankers, and LangChain router chains.
- Design CI orchestrations, including daily Jenkins jobs for delta detection, image captioning (e.g., Qwen2-VL, LLaVA), cost/latency guardrails, and rollback strategies.
- Establish model and prompt governance, including prompt templates, few-shot libraries, safety filters, and evaluation rubrics (faithfulness, coverage, compile success).
- Lead architecture for a UI onboarding tool, deciding on hosting (FastAPI + React or Streamlit MVP), SSO/auth flows, token streaming, and feedback mechanisms for continuous learning.
- Oversee data security and compliance, embedding privacy policies, source citations, audit logs, and ensuring Confluence/Qtest credentials are managed in Secrets Manager.
- Provide technical leadership by reviewing PRs, setting code quality standards, and conducting architecture workshops for AI and Automation Agent Engineers.
- 6–8 years of experience building data or ML platforms, with at least 2 years deploying LLM/RAG systems in production.
- Deep expertise in LangChain, ChromaDB, Qdrant, or pgvector, and cross-encoder rerankers.
- Strong proficiency in Python (FastAPI or Flask) and ability to analyze Java codebases for chunking boundaries.
- Proven experience designing CI/CD pipelines (Jenkins, GitHub Actions) with delta builds and artifact promotion.
- Hands-on experience managing OpenAI/Anthropic API keys or self-hosting large models.
- Demonstrated expertise in security and compliance, including PII protection, role-based access, and secret rotation.
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
#J-18808-Ljbffr-
RAG Architect
2 semanas atrás
Buenos Aires, Brasil Perform Tempo inteiroJoin to apply for the RAG Architect role at Perform We are seeking a Senior AI Engineer to lead the design and implementation of an end-to-end Retrieval-Augmented Generation (RAG) architecture. This role will drive the ingestion of GitHub repositories, Confluence pages, Qtest artifacts, PRDs, and script libraries to power autoscripting, onboarding search,...
-
RAG Architect
2 semanas atrás
Buenos Aires, Espírito Santo, Brazil Perform Tempo inteiroJoin to apply for the RAG Architect role at PerformWe are seeking a Senior AI Engineer to lead the design and implementation of an end-to-end Retrieval-Augmented Generation (RAG) architecture. This role will drive the ingestion of GitHub repositories, Confluence pages, Qtest artifacts, PRDs, and script libraries to power autoscripting, onboarding search, and...
-
Expert GenAI Solutions Architect
2 semanas atrás
Buenos Aires, Brasil beBeeGenaie Tempo inteiro R$100.000 - R$150.000Job Title: Expert GenAI Solutions ArchitectWe are seeking a seasoned GenAI Engineer to drive enterprise-wide AI initiatives forward. Your expertise in building robust GenAI and agentic AI workflows will be pivotal in automating processes across multiple platforms.Design and develop GenAI solutions utilizing prompt engineering, RAG, and custom...
-
Chief Data Architect
1 semana atrás
Buenos Aires, Brasil beBeeData Tempo inteiro US$120.000 - US$150.000About Our TeamWe are seeking a seasoned software engineer to collaborate with our AI product development team in creating cutting-edge, user-centric products. The primary goal is to integrate large language models (LLMs), retrieval-augmented generation (RAG), and cloud-native infrastructure to deliver intelligent business insights.
-
Harnessing the Power of Knowledge: Seeking Experienced AI Leader
2 semanas atrás
Buenos Aires, Brasil beBeeArchitecture Tempo inteiro R$120.000 - R$150.000Senior AI Engineer - RAG ArchitectUnlock community knowledge in a new way. As a Senior AI Engineer, you will lead the design and implementation of an end-to-end Retrieval-Augmented Generation (RAG) architecture to power autoscripting, onboarding search, and long-term knowledge reuse.The ideal candidate is an experienced leader who can oversee multiple...
-
Architect of Scalable AI Solutions
1 semana atrás
Buenos Aires, Espírito Santo, Brazil beBeeInnovation Tempo inteiro US$120.000 - US$150.000Senior AI Engineer - RAG ArchitectAt our organization, we're seeking a visionary Senior AI Engineer to spearhead the development of a cutting-edge Retrieval-Augmented Generation (RAG) architecture. This pivotal role will oversee the ingestion of large datasets, script libraries, and knowledge reuse systems to drive innovation in autoscripting, onboarding...
-
Backend Architect
2 semanas atrás
Buenos Aires, Brasil beBeeDeveloper Tempo inteiro US$118.400 - US$142.900AI Systems DeveloperBuild and implement cutting-edge backend solutions that power real-world AI applications.This role involves working with cloud-based and on-prem LLM APIs, applying prompt engineering techniques, and orchestrating models using modern frameworks like LangChain and LangGraph.The goal is to design and deliver tangible business value across...
-
Buenos Aires, Brasil beBeeEngineer Tempo inteiro R$100.000 - R$125.000Senior AI Engineer LeadWe're building a cutting-edge Retrieval-Augmented Generation (RAG) architecture to unlock community knowledge in a new way. As a Senior AI Engineer Lead, you will lead the design and implementation of this innovative solution.Key ResponsibilitiesArchitect ingestion and retrieval layers, selecting loaders, chunking strategies (AST-aware...
-
Cloud AI Consultant, Professional Services, Cloud
2 semanas atrás
Buenos Aires, Brasil Google Tempo inteiroCloud AI Consultant, Professional Services, Google Cloud (English) Join to apply for the Cloud AI Consultant, Professional Services, Google Cloud (English) role at Google Cloud AI Consultant, Professional Services, Google Cloud (English) 6 days ago Be among the first 25 applicants Join to apply for the Cloud AI Consultant, Professional Services, Google...
-
Backend Developer – GenAI Projects
4 semanas atrás
Buenos Aires, Brasil Kyndryl Tempo inteiroJoin to apply for the Backend Developer – GenAI Projects role at Kyndryl Join to apply for the Backend Developer – GenAI Projects role at Kyndryl Get AI-powered advice on this job and more exclusive features. Who We AreAt Kyndryl, we design, build, manage and modernize the mission-critical technology systems that the world depends on every day. So...