Knowledge Graph Engineer (AI)

Emplay; United States; Remote; USD 100,000 - 150,000; Full time

Job summary

Emplay Analytics Inc is seeking a Graph Expert to design, build, and query knowledge graphs and semantic graphs, with hands-on Neo4j Cypher experience to power AI and data pipelines. You will implement Retrieval-Augmented Generation pipelines, develop LangChain based applications, and integrate Neo4j, Neptune, Bedrock, and vector stores into scalable cloud workflows.

This remote, US-based role targets 2–3 years of experience and pairs with AWS serverless architecture to deploy autonomous AI

Qualifications

• Experience designing knowledge graphs or semantic graphs.
• Hands-on Neo4j Cypher and integrating into AI/data pipelines.
• Experience with graph databases such as Neo4j or Neptune.
• Strong Python fundamentals.
• Experience invoking Amazon Bedrock and prompt engineering.
• Experience building Retrieval-Augmented Generation pipelines.

Responsibilities

• Design and build production-grade knowledge graphs with ontologies.
• Write and optimise Cypher queries using APOC and GDS.
• Integrate Neo4j/Amazon Neptune into AI/data pipelines.
• Build RAG pipelines for document ingestion, embedding, and vector search.
• Develop LangChain-based LLM applications.
• Integrate Bedrock into backend pipelines and agent workflows.
• Design autonomous AI agents with planning and multi-step reasoning.
• Collaborate on AWS serverless architecture to deploy AI components.
• Participate in code reviews and document designs.

Skills

Knowledge Graph Design

Neo4j Cypher

Python

LangChain

AWS Serverless

Graph Analytics

Vector Databases

Agent‑Oriented AI

Tools

Neo4j

APOC

GDS

Bedrock

LangChain

OpenSearch/Elasticsearch

DynamoDB

Job description

Experience - 2-3 years

No of Positions - 4

Location - Remote / Work from Home ,Organization- Emplay Analytics Inc

Salary (CTC) - As per company standards

Role Overview

We are looking for a Graph Expert with strong, demonstrable expertise in graph technologies to join our team. The ideal candidate will have hands‑on experience designing, building, and querying knowledge graphs or semantic graphs, working with Neo4j (Cypher, APOC, GDS), and integrating graph databases into AI and data pipelines. This role sits at the intersection of knowledge graph engineering, LLM‑powered application development, and cloud‑native AI infrastructure.

Key Responsibilities

• Design and build production‑grade knowledge graphs and semantic graphs, defining entities, relationships, ontologies, and graph schemas.
• Write, optimise, and maintain Cypher queries; leverage APOC procedures and Graph Data Science (GDS) library for advanced analytics.
• Integrate Neo4j (or Amazon Neptune) into AI and data pipelines alongside vector databases and relational stores.
• Build and maintain Retrieval‑Augmented Generation (RAG) pipelines covering document ingestion, chunking, embedding generation, vector search, and LLM grounding.
• Develop LLM‑powered applications using LangChain - chains, agents, tools, memory modules, and custom retrievers.
• Integrate Amazon Bedrock to invoke foundation models, manage configurations, and embed them into backend pipelines and agentic workflows.
• Design and implement autonomous or semi‑autonomous AI agents with tool use, planning, and multi‑step reasoning.
• Collaborate on AWS serverless architecture (Lambda, API Gateway, DynamoDB, S3) to deploy and scale AI components.
• Participate in code reviews, communicate blockers early, and take tasks through to completion with minimal supervision.
• Document technical design decisions, graph schemas, and pipeline architecture clearly for cross‑functional audiences.

Core Skills (Required)

Knowledge Graph / Semantic Graph Construction

• Experience designing and building knowledge graphs or semantic graphs.
• Understanding of entities, relationships, graph schema design, ontology modelling, and querying graph data.
• Hands‑on experience with Neo4j strongly preferred: Cypher query language, graph data modelling, and integrating Neo4j into AI or data pipelines.

Graph Databases

• Hands‑on experience with graph databases such as Neo4j or Amazon Neptune.
• Understanding of graph storage models, indexing, querying, and when to choose a graph database over relational or document stores.

Python

• Strong fundamentals: typing, async/await, decorators, context managers, OOP concepts, and robust error handling.

Amazon Bedrock

• Practical experience invoking foundation models, managing model configurations, and prompt engineering via Amazon Bedrock.
• Experience integrating Bedrock into backend pipelines and agent workflows.
• Hands‑on experience building Retrieval‑Augmented Generation pipelines: document ingestion, chunking strategies, embedding generation, vector search, retrieval, and grounding LLM responses.

LangChain

• Practical experience building LLM‑powered applications with LangChain: chains, agents, tools, memory modules, and retrievers.
• Familiarity integrating LangChain with external data sources and APIs.
• Comfortable with code reviews, communicating blockers, and discussing technical trade‑offs.
• Able to independently investigate unfamiliar problems, close knowledge gaps, and drive tasks to completion.

Preferred Skills

Advanced Graph Analytics

• Experience with graph algorithms: shortest path, centrality, community detection, and graph traversal strategies.
• Applying graph‑based reasoning to enhance retrieval and contextual grounding in AI systems.

Neo4j Ecosystem

• Deep familiarity with Cypher, APOC procedures, Graph Data Science (GDS) library, and integrating Neo4j with Python‑based AI pipelines.

AWS Services

• Hands‑on experience with Lambda, API Gateway, DynamoDB, and S3.
• Understanding of serverless architecture, IAM roles and permissions, and event‑driven patterns.

A2A (Agent-to-Agent Communication)

• Understanding of agent‑to‑agent communication patterns and protocols.
• Experience building multi‑agent systems where agents collaborate, delegate tasks, or exchange context.
• Understanding of MCP as a standard for connecting AI models to tools, data sources, and external systems.
• Experience building or integrating MCP servers/clients into agentic architectures.

Vector Databases

• Exposure to vector databases such as Amazon OpenSearch and Elasticsearch for storing and querying embeddings in RAG workflows.

AI Agents & Agentic Workflows

• Experience designing and building autonomous or semi‑autonomous AI agents.
• Understanding of agent loops, tool use, memory, planning, and multi‑step reasoning patterns.