AI RAG Engineer X2

We are excited to be continuously expanding our team.

Job: AI RAG Engineer X2

Location:

Remote

Duration: 12 Months

Rate: $85 to $90

Position Summary

We are seeking two experienced AI RAG Engineers to design, develop, and deploy production-grade Generative AI solutions, Retrieval-Augmented Generation (RAG) systems, LLM-powered applications, AI agents, knowledge retrieval platforms, and intelligent automation solutions. The ideal candidates will have strong hands‑on experience with Python, Large Language Models (LLMs), vector databases, embeddings, prompt engineering, RAG architectures, REST APIs, cloud platforms, and AI application development.

Experience with enterprise data, security, observability, and production deployment is highly desirable.

1. AI Solution Development

Design, develop, and deploy production-grade Generative AI and RAG applications.

Build end-to-end AI solutions using LLMs, embeddings, vector databases, retrieval pipelines, and enterprise data sources.

Develop intelligent applications that combine LLM reasoning with enterprise knowledge and business processes.

Implement document ingestion, parsing, chunking, embedding generation, indexing, retrieval, reranking, and response generation pipelines.

Develop AI agents and agentic workflows that interact with tools, APIs, databases, and enterprise applications.

Integrate LLM solutions with REST APIs, databases, cloud services, and existing enterprise systems.

Evaluate and select appropriate LLMs, embedding models, vector stores, and AI frameworks based on business and technical requirements.

Develop reusable AI components, services, APIs, and frameworks.

Apply prompt engineering and structured output techniques to improve accuracy and reliability.

2. RAG Engineering

Design scalable Retrieval-Augmented Generation architectures for enterprise use cases.

Develop ingestion pipelines for structured and unstructured data.

Implement semantic and hybrid search using vector databases and search technologies.

Optimize document chunking, metadata strategies, embeddings, retrieval, filtering, and reranking.

Improve retrieval accuracy, relevance, grounding, and response quality.

Develop strategies for managing large knowledge bases and continuously changing enterprise data.

Implement citations, source attribution, and traceability for AI-generated responses.

Analyze retrieval failures and hallucinations and implement corrective improvements.

Develop evaluation frameworks to measure retrieval quality, answer relevance, factuality, and task completion.

3. AI and Agentic Application Development

Build LLM-powered applications, intelligent assistants, and enterprise AI solutions.

Design agentic workflows using Lang Graph, Lang Chain, Semantic Kernel, or similar frameworks.

Implement tool/function calling and integrations with enterprise systems.

Design multi-step workflows involving planning, retrieval, reasoning, tool execution, validation, and response generation.

Implement agent memory and state management where appropriate.

Develop guardrails to control agent behavior, tool access, and generated responses.

Design human-in-the-loop workflows for high-risk or business-critical processes.

Optimize AI applications for accuracy, latency, scalability, and cost.

4. Software Engineering

Develop clean, maintainable, and production-ready Python applications.

Build RESTful APIs and microservices supporting AI applications.

Apply software engineering best practices, including version control, testing, code reviews, CI/CD, and documentation.

Work with relational and No

SQL databases and data-processing technologies.

Develop automated unit, integration, and end-to-end tests for AI applications.

Collaborate with cloud and Dev Ops teams to deploy AI…