Senior Data Engineer (Agentic Retrieval & Memory Systems) | Vish Consulting Services (VISHUSA) | Oaks, Pennsylvania, USA

Vish Consulting Services (VISHUSA); Oaks (PA); Hybrid; USD 150,000 - 210,000; Full time

Job summary

Vish Consulting Services (VISHUSA) seeks a Senior Data Engineer to design and implement Agentic Retrieval architectures and memory systems for enterprise AI platforms in a hybrid Oaks, PA setting.

Lead data pipelines, vector search, and RAG solutions using PostgreSQL with pgvector, Azure AI, and LLMs. Collaborate with AI engineers and business stakeholders to deliver scalable AI data solutions with strong governance.

Qualifications

• Bachelor’s or Master’s degree in CS/data engineering/AI/software engineering.
• Minimum 12 years of data engineering or data platform experience.
• Proven hands-on with Agentic Retrieval architectures (mandatory).
• Strong knowledge of LLMs and AI-powered enterprise systems.
• Extensive experience implementing RAG solutions and Azure AI services.
• Hands-on with PostgreSQL and pgvector; strong data modeling and SQL.

Responsibilities

• Design and implement enterprise Agentic Retrieval architectures and memory systems.
• Build scalable Retrieval-Augmented Generation pipelines leveraging structured and unstructured data.
• Develop vector search and semantic retrieval solutions using PostgreSQL with pgvector.
• Design memory frameworks to support contextual reasoning and long-term AI agent capabilities.
• Collaborate with AI engineers and stakeholders to translate requirements into scalable architectures.
• Ensure data quality, governance, security, and operational reliability across AI environments.
• Support deployment, monitoring, and optimization of AI systems.

Skills

Agentic Retrieval architectures

Memory architectures

LLMs

RAG

Azure AI services

PostgreSQL

pgvector

Vector databases

NoSQL

SQL

Data pipelines

API design

Data governance/security

Education

Bachelor’s or Master’s Degree in Computer Science/Data Engineering/AI/Software Engineering

Tools

PostgreSQL

pgvector

Azure AI

LangChain

LangGraph

Databricks

Spark

MLOps

Job description

Senior Data Engineer (Agentic Retrieval & Memory Systems) | Vish Consulting Services (VISHUSA) | Oaks, Pennsylvania, USA

Recruiting Company: Vish Consulting Services (VISHUSA)

Job Location: Oaks, Pennsylvania, USA (Hybrid)

Job Type: Contract (C2C)

Position Summary

Vish Consulting Services is seeking a highly experienced Senior Data Engineer specializing in Agentic Retrieval, Memory Architectures, and Enterprise AI Platforms. This role focuses on building intelligent data retrieval systems, advanced knowledge architectures, and Large Language Model (LLM)-driven enterprise solutions that power next-generation AI applications.

Detailed Job Description

As a Senior Data Engineer, you will design and develop sophisticated retrieval, memory, and knowledge management systems for enterprise AI platforms. You will work closely with AI engineers, data scientists, architects, and business stakeholders to build scalable Agentic AI solutions leveraging vector search, memory frameworks, and advanced retrieval techniques. The role requires deep expertise in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), Azure AI technologies, vector databases, and modern data engineering practices. You will be responsible for developing high-performance AI data pipelines that enable intelligent reasoning, contextual memory, and enterprise-scale information retrieval. This is an excellent opportunity to work on cutting-edge AI systems that combine data engineering, machine learning, and intelligent automation.

Key Responsibilities

• Design and implement enterprise Agentic Retrieval architectures and intelligent memory systems.
• Build scalable Retrieval-Augmented Generation (RAG) pipelines leveraging structured and unstructured data.
• Develop vector search and semantic retrieval solutions using PostgreSQL with pgvector and related technologies.
• Design memory frameworks to support contextual reasoning and long-term AI agent capabilities.
• Work with Large Language Models (LLMs) to optimize retrieval quality, context management, and response generation.
• Develop data pipelines, ingestion frameworks, and indexing processes for AI-driven applications.
• Integrate Azure AI services and enterprise data platforms into intelligent retrieval systems.
• Optimize vector databases, embeddings, search relevance, and retrieval performance.
• Develop APIs and backend services supporting AI-powered data solutions.
• Collaborate with AI engineers and stakeholders to translate business requirements into scalable architectures.
• Ensure data quality, governance, security, and operational reliability across AI environments.
• Support production deployment, monitoring, and optimization of enterprise AI systems.

Required Qualifications & Skills

• Bachelor’s or Master’s Degree in Computer Science, Data Engineering, Artificial Intelligence, Software Engineering, or a related field.
• Minimum 12 years of experience in Data Engineering, Data Architecture, or Enterprise Data Platforms.
• Proven hands‑on experience with Agentic Retrieval architectures (Mandatory).
• Strong understanding of Large Language Models (LLMs) and AI-powered enterprise systems.
• Extensive experience implementing Retrieval-Augmented Generation (RAG) solutions.
• Strong expertise in Azure AI services and enterprise cloud-based AI platforms.
• Hands‑on experience with PostgreSQL and pgvector.
• Strong knowledge of Vector Databases and embedding technologies.
• Experience working with NoSQL databases and large-scale distributed data environments.
• Deep understanding of memory architectures for AI agents and intelligent systems.
• Strong SQL development and data modeling skills.
• Experience designing highly scalable and production-ready AI data solutions.
• Excellent analytical, problem-solving, and stakeholder communication skills.

Nice-to-Have Skills

• Experience with Knowledge Graphs and Graph Databases.
• Exposure to LangChain, LangGraph, AutoGen, CrewAI, or Agentic AI frameworks.
• Experience with Databricks, Spark, and distributed data processing platforms.
• Knowledge of MLOps, LLMOps, and AI observability frameworks.
• Experience building enterprise AI copilots and intelligent automation platforms.