Design and implement Retrieval-Augmented Generation (RAG) solutions using enterprise knowledge repositories and vector databases. * Build conversational memory, session management, and context-aware ...
Quick apply
Design and implement Retrieval-Augmented Generation (RAG) solutions using enterprise knowledge repositories and vector databases. * Build conversational memory, session management, and context-aware ...
Quick apply
Design and implement Retrieval-Augmented Generation (RAG) solutions using enterprise knowledge repositories and vector databases. * Build conversational memory, session management, and context-aware ...
Manhattan, NY · On-site
$76 - $98/hr
... of vector databases, semantic search, embeddings, and enterprise AI retrieval patterns. • Familiarity with AI orchestration frameworks and libraries such as LangChain, Semantic Kernel, AutoGen ...
Manhattan, NY · On-site
$76 - $98/hr
... of vector databases, semantic search, embeddings, and enterprise AI retrieval patterns. • Familiarity with AI orchestration frameworks and libraries such as LangChain, Semantic Kernel, AutoGen ...
Long Beach, NY · On-site
$147.90 - $254.80/hr
Oversee vector database design (Azure AI Search or equivalent) and integration with Snowflake/Fabric data hubs. Implement high‑availability, cost‑optimized compute and storage strategies for AI ...
Long Beach, NY · On-site
$147.90 - $254.80/hr
Oversee vector database design (Azure AI Search or equivalent) and integration with Snowflake/Fabric data hubs. Implement high‑availability, cost‑optimized compute and storage strategies for AI ...
Design and implement Retrieval-Augmented Generation (RAG) solutions using enterprise knowledge repositories and vector databases. * Build conversational memory, session management, and context-aware ...
Design and implement Retrieval-Augmented Generation (RAG) solutions using enterprise knowledge repositories and vector databases. * Build conversational memory, session management, and context-aware ...
Brooklyn, NY · On-site
$132K - $177K/yr
LangChain, LangGraph, LlamaIndex, NLP models, RAG vector DBs, model deployment. • 7+ years database: Oracle SQL/PL-SQL, ER design, query optimization. • 7+ years microservices/web: REST APIs, MVC ...
Brooklyn, NY · On-site
$132K - $177K/yr
LangChain, LangGraph, LlamaIndex, NLP models, RAG vector DBs, model deployment. • 7+ years database: Oracle SQL/PL-SQL, ER design, query optimization. • 7+ years microservices/web: REST APIs, MVC ...
Edison, NJ · On-site
Knowledge of SAP HANA Cloud, SAP Data Intelligence, SAP Analytics Cloud, vector databases, and knowledge graphs. * Understanding of Agent-to-Agent (A2A) communication and Model Context Protocol (MCP ...
Edison, NJ · On-site
Knowledge of SAP HANA Cloud, SAP Data Intelligence, SAP Analytics Cloud, vector databases, and knowledge graphs. * Understanding of Agent-to-Agent (A2A) communication and Model Context Protocol (MCP ...
Brooklyn, NY · On-site
$132K - $177K/yr
LangChain, LangGraph, LlamaIndex, NLP models, RAG vector DBs, model deployment. • 7+ years database: Oracle SQL/PL-SQL, ER design, query optimization. • 7+ years microservices/web: REST APIs, MVC ...
Brooklyn, NY · On-site
$132K - $177K/yr
LangChain, LangGraph, LlamaIndex, NLP models, RAG vector DBs, model deployment. • 7+ years database: Oracle SQL/PL-SQL, ER design, query optimization. • 7+ years microservices/web: REST APIs, MVC ...
Build hybrid retrieval systems combining Knowledge Graphs + vector databases * Integrate structured graph reasoning with LLMs to reduce hallucination and improve explain ability
Build hybrid retrieval systems combining Knowledge Graphs + vector databases * Integrate structured graph reasoning with LLMs to reduce hallucination and improve explain ability
New York, NY · On-site
$126K - $145K/yr
Pinecone is the leading vector database for building accurate and performant AI applications at scale in production. Pinecone's mission is to make AI knowledgeable. More than 109,000 customers across ...
New York, NY · On-site
$126K - $145K/yr
Pinecone is the leading vector database for building accurate and performant AI applications at scale in production. Pinecone's mission is to make AI knowledgeable. More than 109,000 customers across ...
Build hybrid retrieval systems combining Knowledge Graphs + vector databases * Integrate structured graph reasoning with LLMs to reduce hallucination and improve explainability
Build hybrid retrieval systems combining Knowledge Graphs + vector databases * Integrate structured graph reasoning with LLMs to reduce hallucination and improve explainability
... vector databases and embedding systems to power similarity search, identity linking, and reusable identity experiences. • Partner closely with Product, Engineering, and Risk teams to deliver ...
... vector databases and embedding systems to power similarity search, identity linking, and reusable identity experiences. • Partner closely with Product, Engineering, and Risk teams to deliver ...
New York, NY · On-site
$220K/yr
Built production systems using LLMs, vector databases, and retrieval pipelines. * Thrived in an early-stage startup. * U.S. Person status required. May involve export-controlled data. Bonus if you've.
New York, NY · On-site
$220K/yr
Built production systems using LLMs, vector databases, and retrieval pipelines. * Thrived in an early-stage startup. * U.S. Person status required. May involve export-controlled data. Bonus if you've.
Built production systems using LLMs, vector databases, and retrieval pipelines. * Thrived in an early-stage startup. * U.S. Person status required. May involve export-controlled data. Bonus if you've.
Built production systems using LLMs, vector databases, and retrieval pipelines. * Thrived in an early-stage startup. * U.S. Person status required. May involve export-controlled data. Bonus if you've.
... vector databases and embedding systems to power similarity search, identity linking, and reusable identity experiences. • Partner closely with Product, Engineering, and Risk teams to deliver ...
... vector databases and embedding systems to power similarity search, identity linking, and reusable identity experiences. • Partner closely with Product, Engineering, and Risk teams to deliver ...
$100K - $160K/yr
Building and optimizing RAG (Retrieval-Augmented Generation) pipelines with vector databases * Developing AI agents and multi-agent orchestration systems using frameworks like LangChain or LlamaIndex
$100K - $160K/yr
Building and optimizing RAG (Retrieval-Augmented Generation) pipelines with vector databases * Developing AI agents and multi-agent orchestration systems using frameworks like LangChain or LlamaIndex
New York, NY · On-site
$100K - $160K/yr
Building and optimizing RAG (Retrieval-Augmented Generation) pipelines with vector databases * Developing AI agents and multi-agent orchestration systems using frameworks like LangChain or LlamaIndex
Quick apply
New York, NY · On-site
$100K - $160K/yr
Building and optimizing RAG (Retrieval-Augmented Generation) pipelines with vector databases * Developing AI agents and multi-agent orchestration systems using frameworks like LangChain or LlamaIndex
Manhattan, NY · On-site
$69.50 - $91.50/hr
Understanding of data pipelines and vector databases * Strong problem-solving and communication skills
Manhattan, NY · On-site
$69.50 - $91.50/hr
Understanding of data pipelines and vector databases * Strong problem-solving and communication skills
New York, NY · On-site
$100K - $175K/yr
Zilliz is a fast-growing startup developing the industry's leading vector database for enterprise-grade AI. Founded by the engineers behind Milvus, the world's most popular open-source vector ...
New York, NY · On-site
$100K - $175K/yr
Zilliz is a fast-growing startup developing the industry's leading vector database for enterprise-grade AI. Founded by the engineers behind Milvus, the world's most popular open-source vector ...
New York, NY · On-site
$140K - $160K/yr
Deep understanding of vector databases, RAG pipelines, embeddings, and prompt engineering.
Quick apply
New York, NY · On-site
$140K - $160K/yr
Deep understanding of vector databases, RAG pipelines, embeddings, and prompt engineering.
Manhattan, NY · On-site
Deep understanding of vector databases, RAG pipelines, embeddings, and prompt engineering.
Manhattan, NY · On-site
Deep understanding of vector databases, RAG pipelines, embeddings, and prompt engineering.
| Aspect | Vector Databases | Data Engineers |
|---|---|---|
| Required Skills | Database management, data modeling, query optimization | Data pipeline development, ETL processes, programming |
| Work Environment | Data storage systems, AI/ML projects, cloud platforms | Data infrastructure, cloud environments, big data tools |
| Industry Usage | AI, machine learning, recommendation systems | Data integration, analytics, data architecture |
While Vector Databases focus on storing and querying high-dimensional vector data for AI applications, Data Engineers build and maintain data pipelines and infrastructure to support data analysis and machine learning workflows. Both roles are essential in data-driven industries but serve different functions within the data ecosystem.
Contractor
Posted 10 days ago
About the Role
We are looking for an experienced Senior AI Agent Engineer to lead the design and development of enterprise-grade AI agents using Google Agent Development Kit (ADK) and Google Gemini. This role is ideal for someone passionate about building intelligent, autonomous systems that can reason, plan, collaborate, and execute business workflows across enterprise applications.
You will work closely with product managers, architects, and business stakeholders to develop AI-powered solutions that integrate seamlessly with Google Workspace, Google Cloud, internal platforms, and third-party enterprise systems. The ideal candidate has strong software engineering fundamentals, hands-on experience with Generative AI technologies, and a proven ability to deliver production-ready AI solutions.
Key ResponsibilitiesSourced by ZipRecruiter
First Soft Solutions custom application Development and Maintenance Services are designed to enable you to lower the total cost of ownership and the required quality for your application. While all application Development Outsourcing is Technically custom, The difference is that packaged applications were designed with a general set of features to be used by a broad range of users. Custom application development is capable of producing practically any feature you may desire for your site. Time and money are virtually the only limiting factors. Our goal is to provide Clients with the Solution that fits their specific and unique needs while giving them the knowledge they need to operate and maintain the New Systems and Software. Our allegiance is to the best solution for our Clients. Our experience and knowledgeable consultants are ready to go above and beyond expectations to assist you in obtaining your goals. We can also provides expert project management throughout the entire project life cycle.
It services
11 - 50 Employees
East Brunswick, NJ, US
2006