RAG Architect

FyerX - Your Trusted Marketing Partner

. Architect end-to-end advanced Retrieval-Augmented Generation (RAG) pipelines for document parsing, semantic metadata enrichment, and multi-vector lookups .

Posted 9/23/2026contractRemote • IndiaMid-LevelSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in architecting advanced Retrieval-Augmented Generation (RAG) pipelines and optimizing context retrieval for live LLM applications. Proficient in managing enterprise generative AI performance metrics and implementing automated data chunking and caching architectures.

Highest-signal resume keywords

Python MasteryVector Database ExpertiseText Embedding Model ProficiencyGoogle Cloud Certified Professional Cloud Database EngineerAWS Certified Data Analytics - Specialty

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Data EngineeringDatabase DesignSearch Engine EngineeringContext Retrieval ScalingMachine Learning Cross-EncodersSQLHybrid Search AlgorithmsGraph RAG FrameworksAutomated Data ChunkingSemantic Caching Architectures

Tools & Technologies

PineconeMilvusWeaviateLlamaIndexLangChainGPTCacheCohere RerankBGE-RerankerNeo4j

Certifications & Qualifications

Google Cloud Certified Professional Cloud Database EngineerAWS Certified Data Analytics - SpecialtyDatabricks Certified Data Engineer Professional

Industry Keywords

Retrieval-Augmented GenerationContext Window LimitationsMulti-Vector LookupsSemantic Metadata EnrichmentPrecision MetricsRetrieval Recall BoundsCloud Memory SpacesNetwork Data Transfer SpeedsAutomated Semantic CachingFine-Tuning Open-Source Models

Tech Stack

Tools & technologies

AWSAzureCloudGoogle Cloud PlatformNeo4jPythonSQL

About the role

Key responsibilities & impact

Architect end-to-end advanced Retrieval-Augmented Generation (RAG) pipelines for document parsing, semantic metadata enrichment, and multi-vector lookups
Optimize context window utilization through parent-child chunking models, sentence-window retrievals, and sliding window strategies
Build high-performance re-ranking layers using machine learning cross-encoders such as Cohere Rerank and BGE-Reranker
Implement automated semantic caching architectures using caching layers such as GPTCache
Establish automated data chunking pipelines for PDFs, corporate wikis, and SQL outputs
Govern vector similarity spaces by fine-tuning hybrid search algorithms combining dense semantic embeddings with sparse keyword token indexes such as BM25
Audit context-level hallucination rates and accuracy logs, tracking precision metrics, retrieval recall bounds, and processing speeds
Own enterprise generative AI retrieval performance, accuracy, and operational cost metrics

Requirements

What you’ll need

6 to 10 years of enterprise data engineering, database design, or search engine engineering experience
3+ dedicated years actively scaling context retrieval loops for live LLM applications
Mandatory certification: Google Cloud Certified Professional Cloud Database Engineer, AWS Certified Data Analytics - Specialty, Databricks Certified Data Engineer Professional, or equivalent Professional Cloud Data/Database Engineer or Specialty Analytics credential from a major cloud vendor (AWS/GCP/Azure)
Strong technical mastery of Python
Strong technical mastery of vector databases, including Pinecone, Milvus, and Weaviate
Strong technical mastery of text embedding models
Strong technical mastery of open-source orchestration tools, including LlamaIndex and LangChain
Strong technical mastery of SQL
Deep structural understanding of context window limitations, including the “lost in the middle” phenomenon
Understanding of multi-modal token dynamics
Understanding of network data transfer speeds
Understanding of cloud memory spaces
Prior experience implementing Graph RAG frameworks utilizing native knowledge graphs, such as Neo4j (preferred)
Familiarity with fine-tuning open-source text embedding models for industry-specific terminology or legacy product schemas (preferred)

Benefits

Comp & perks

Remote work arrangement
Contract employment