RAG Engineer

MCI Careers•,

7d•Onsite

About The Position

MCI is seeking a highly skilled RAG Engineer to build Retrieval-Augmented Generation (RAG) systems that combine the power of Large Language Models with enterprise knowledge and information retrieval technologies. This role is focused on creating AI solutions that deliver accurate, context-aware responses by leveraging structured and unstructured organizational data. You will play a key role in developing scalable knowledge systems that enhance AI reliability, trust, and business impact. To be considered for this role, you must complete a full application on our company careers page, including all screening questions and a brief pre-employment test.

Requirements

Bachelor's Degree in Computer Science, Information Systems, Data Science, Artificial Intelligence, Software Engineering, or a related field.
Minimum 3 years of experience in software engineering, AI engineering, machine learning, or information retrieval.
Strong proficiency in Python and experience developing production-grade applications.
Experience building APIs, microservices, or cloud-native applications.
Solid understanding of Large Language Models (LLMs) and Generative AI concepts.
Experience designing and implementing Retrieval-Augmented Generation (RAG) solutions.
Understanding of embeddings, vectorization techniques, and semantic search methodologies.
Experience working with structured and unstructured data sources.
Knowledge of data ingestion, indexing, and retrieval pipelines.
Familiarity with cloud platforms such as AWS, Azure, or Google Cloud Platform.
Strong analytical, troubleshooting, and problem-solving skills.
Excellent communication and stakeholder engagement abilities.

Nice To Haves

Experience with Pinecone, Weaviate, Milvus, Chroma, or similar vector databases.
Experience with LangChain, LlamaIndex, Haystack, or related frameworks.
Knowledge of knowledge management and enterprise search platforms.
Exposure to MLOps practices and AI deployment pipelines.
Experience building conversational AI or chatbot solutions.
Familiarity with containerization technologies such as Docker and Kubernetes.
Understanding of AI governance, security, and compliance requirements.
Experience working within Agile development environments.

Responsibilities

Design and maintain Retrieval-Augmented Generation solutions that provide accurate and context-aware responses.
Build document ingestion, indexing, and retrieval pipelines.
Develop enterprise knowledge repositories and search frameworks.
Implement semantic search capabilities across structured and unstructured data.
Design scalable architectures supporting AI-powered knowledge retrieval.
Optimize retrieval performance and relevance across AI applications.
Implement and manage vector databases and embedding pipelines.
Improve retrieval quality through tuning and evaluation.
Optimize latency, scalability, and search effectiveness.
Maintain data quality and knowledge management standards.
Support the integration of retrieval systems with AI applications.
Collaborate with AI engineers and product teams on solution design.
Integrate retrieval services with Large Language Models.
Develop APIs and services that support AI workflows.
Ensure reliable access to enterprise knowledge sources.
Maintain operational excellence across RAG environments.
Monitor retrieval accuracy and system performance.
Implement governance and data security controls.
Troubleshoot retrieval and indexing issues.
Maintain documentation and operational procedures.
Drive continuous improvement in retrieval technologies and methodologies.
Evaluate emerging retrieval frameworks and search technologies.
Research new approaches to knowledge management and retrieval optimization.
Recommend enhancements to improve user experience and AI performance.
Contribute to AI architecture and innovation initiatives.