Senior AI Data Engineer (Vector Database & RAG Platform) | Marc Ellis | Remote, India

Marc Ellis; India; Remote; INR 4,000,000 - 6,500,000; Full time

Job summary

Marc Ellis is seeking a Senior AI Data Engineer to design, build, and operate enterprise-grade vector database and RAG platforms that support AI and GenAI solutions. You will architect data infrastructure, develop production-grade pipelines, and ensure governance and security across enterprise AI initiatives.

The role requires hands-on experience with vector databases, embeddings, and LLM integration, plus strong Python and SQL skills.

Qualifications

• 8+ years of experience in Data Engineering or related fields.
• 3+ years hands-on with AI/ML data platforms, vector databases or GenAI.
• 2+ years building production-grade RAG solutions.
• Strong Python programming and SQL skills.
• Experience with vector DBs and LLM integration.
• Knowledge of CI/CD, containers, and DevOps practices.
• Experience across cloud, hybrid, or on‑prem environments.
• Understanding of data governance, security, lineage, and audit controls.
• Excellent analytical and technical communication skills.

Responsibilities

• Design and manage enterprise-scale vector database architectures and retrieval services.
• Build production-grade RAG pipelines including ingestion, embeddings, indexing, retrieval, and response generation.
• Develop scalable data pipelines for structured and unstructured data.
• Integrate vector databases with LLMs and AI applications.
• Implement semantic/hybrid search and relevance optimization.
• Establish governance, metadata, lineage, and access controls.
• Optimize retrieval accuracy, latency, and platform performance.
• Develop monitoring and observability for AI data platforms.
• Collaborate with AI, data science, and engineering teams to enable enterprise AI initiatives.
• Create reusable standards and best practices for AI platform development.
• Ensure security, audit, and regulatory compliance.
• Participate in architecture reviews and technology evaluations.

Skills

Python

SQL

AI/ML platforms

RAG pipelines

LLM integration

APIs

CI/CD

DevOps

Data governance

Semantic search

Education

Bachelor's or Master's degree

Tools

Oracle AI Vector Search

Milvus

Pinecone

Weaviate

Qdrant

pgVector

Databricks

Apache Spark

Kafka

Apache Airflow

Job description

Job Title: Senior AI Data Engineer (Vector Database & RAG Platform) | Marc Ellis | Remote, India

Recruiting Company: Marc Ellis

Job Location: Remote (Offshore), India

Job Type: Contract

Contract Duration: 1 Year (Extendable)

Experience Required: 8+ Years

Notice Period: Up to 30 Days

Specialization: Artificial Intelligence (AI), Generative AI (GenAI), Vector Databases, Retrieval-Augmented Generation (RAG)

Position Summary Marc Ellis is seeking a highly experienced Senior AI Data Engineer to design, build, and operationalize enterprise-grade Vector Database and Retrieval-Augmented Generation (RAG) platforms that power next-generation AI and Generative AI solutions. This role is ideal for professionals who have hands-on experience building scalable AI data platforms from the ground up and are passionate about enabling intelligent enterprise applications through modern AI architectures.

Detailed Job Description As a Senior AI Data Engineer, you will play a critical role in architecting and managing the core data infrastructure that supports enterprise AI initiatives. You will be responsible for designing vector database ecosystems, developing production-grade RAG pipelines, and implementing scalable retrieval services that enable advanced Large Language Model (LLM) applications. Working closely with AI engineers, architects, data scientists, and business stakeholders, you will establish governance standards, optimize retrieval performance, and ensure the security and reliability of enterprise AI platforms. The ideal candidate combines expertise in data engineering, semantic search, vector databases, and GenAI technologies with the ability to build robust, scalable, and compliant AI solutions. This is an exciting opportunity to shape enterprise AI capabilities within a rapidly evolving technology landscape.

Key Responsibilities

• Design, implement, and manage enterprise-scale vector database architectures and retrieval services.
• Build production-grade Retrieval-Augmented Generation (RAG) pipelines including ingestion, chunking, embeddings, indexing, retrieval, reranking, and response generation.
• Develop scalable data pipelines for structured and unstructured data sources.
• Integrate vector databases with Large Language Models (LLMs) and AI applications.
• Implement semantic search, hybrid search, and relevance optimization strategies.
• Establish data governance, metadata management, lineage tracking, and access control frameworks.
• Optimize retrieval accuracy, scalability, latency, and platform performance.
• Develop monitoring, observability, and operational processes for AI data platforms.
• Collaborate with AI, data science, and engineering teams to support enterprise AI initiatives.
• Create reusable standards, frameworks, and best practices for AI platform development.
• Ensure compliance with security, audit, regulatory, and governance requirements.
• Participate in architecture reviews, technology evaluations, and strategic AI platform initiatives.

Required Qualifications & Skills

• Bachelor's or Master's degree in Computer Science, Data Engineering, Artificial Intelligence, Information Technology, or a related field.
• 8+ years of experience in Data Engineering, Data Platforms, Artificial Intelligence, or related domains.
• 3+ years of hands-on experience working with AI/ML data platforms, semantic search, vector databases, or Generative AI technologies.
• 2+ years of experience building and deploying production-grade RAG solutions.
• Strong expertise in Python programming and software development.
• Advanced SQL and data engineering skills.
• Hands-on experience with vector database technologies such as Oracle AI Vector Search, Milvus, Pinecone, Weaviate, Qdrant, or pgVector.
• Deep understanding of embeddings, semantic search, hybrid retrieval methods, reranking, and LLM integration.
• Experience developing APIs and scalable AI services.
• Knowledge of CI/CD pipelines, containerization, and DevOps practices.
• Experience working across cloud, hybrid, or on-premises environments.
• Strong understanding of data governance, security, lineage, metadata management, and audit controls.
• Excellent analytical, problem-solving, and technical communication skills.

Nice-to-Have Skills

• Experience within banking, financial services, or other highly regulated industries.
• Hands-on experience with LangChain, LlamaIndex, CrewAI, or similar AI orchestration frameworks.
• Experience with Databricks, Apache Spark, Kafka, or Apache Airflow.
• Knowledge of MLOps, AI observability, and model lifecycle management.
• Experience building enterprise AI platforms from inception through production.
• Familiarity with knowledge graphs, multimodal AI systems, and advanced retrieval architectures.
• Experience supporting large-scale AI transformation initiatives.

Recruitment Pro Tip

For enterprise AI engineering roles, employers look for candidates who can demonstrate real-world production deployments rather than proofs of concept. Highlight specific RAG platforms, vector database implementations, retrieval optimization techniques, LLM integrations, governance frameworks, and measurable outcomes such as improved retrieval accuracy, reduced latency, increased scalability, or successful deployment of enterprise GenAI solutions serving business-critical use cases.