RAG Architect

Job not on LinkedIn

🔥 3 hours ago

🇮🇳 India – Remote

⏳ Contract/Temporary

🟡 Mid-level

🟠 Senior

🏛️ Architect

👻 Ghost score 12%

What it means: how likely this posting is sitting open without active hiring.How to read it: 60% or higher means we think this is a ghost. Lower scores are less of a worry.How we score it: age, reposts, open roles vs team size, how fast jobs close, and whether pay is listed.Fine print: an estimate from public data, not a judgment of the company. Real jobs can score high, so treat it as a hint, not a fact.

Apply Now

Find Similar Remote Jobs

Set Up Email Alert For New Jobs

📊 Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Upload Resume

FyerX - Your Trusted Marketing Partner

WebsiteLinkedInAll Job Openings

11 - 50 employees

Founded 2021

📣 Marketing

🤝 B2B

Marketing • B2B

FyerX is a marketing agency based in Bangalore that specializes in helping businesses enhance their digital presence and improve online outcomes through tailored marketing strategies. With a passionate team of marketing experts, FyerX focuses on various aspects of digital marketing including social media marketing, branding, search engine optimization, and influencer marketing. They aim to fuel the growth of purpose-driven brands by developing integrated marketing plans that drive online growth and improve brand visibility.

📋 Description

• 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

• 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

• Remote work arrangement • Contract employment