RAG Arcitect/Engineer

NTT DATA Services•Dallas, TX

1d•Onsite

About The Position

As a RAG Architect / Engineer, you will be responsible for overseeing the design and implementation of enterprise-grade GenAI RAG solutions that solve complex business problems. You will work closely with product managers, software engineers, data scientists, and key stakeholders to conceptualize, prototype, test, and release robust GenAI solutions. In this dual role, you will act as both the technical authority and a core hands-on contributor across all aspects of our GenAI infrastructure, services, and structural vector databases.

Requirements

Minimum 5+ years of professional, practical experience building and deploying enterprise AI applications.
Advanced understanding of LLMs, NLP, and advanced ML algorithms.
Extensive hands-on experience designing RAG architectures and AI Agents.
Minimum 3+ years of dedicated experience utilizing pre-trained language models (e.g., GPT, BERT, RoBERTa) via APIs or frameworks like Hugging Face for downstream NLP production tasks.
Minimum 3+ years of professional experience utilizing core NLP libraries (NLTK, SpaCy, Gensim, BERT, SBERT models) and modern orchestration frameworks (LangChain, LangGraph, or EmbedChain) to build and deploy GenAI applications.
Minimum 5+ years of professional experience in Python (or similar enterprise programming languages).
Excellent problem-solving skills.
Ability to drive results in a fast-paced, collaborative team environment.
Bachelor’s degree in Computer Science, Data Science, or equivalent practical work experience.

Nice To Haves

Proficiency in designing and deploying GenAI workloads using Azure or AWS Cloud Platforms.

Responsibilities

Design and optimize the foundational structure for vector databases to seamlessly accommodate LLM models across multiple enterprise GenAI tools.
Architect, develop, and scale the infrastructure for GenAI systems, including data storage, processing, and high-performance retrieval mechanisms.
Lead the technical decision-making process regarding architectural choices with external GenAI service providers (e.g., Microsoft Azure, AWS) to ensure solutions are scalable, maintainable, and cost-effective.
Collaborate directly with Business Partners, product owners, and software engineers to translate complex business requirements into enterprise-level GenAI solutions.
Drive model optimization and fine-tuning strategies for large language models to maximize performance, lower latency, optimize memory utilization, and increase throughput.
Present and demo architectural designs and analysis results clearly to non-technical audiences, breaking down complex AI/ML concepts into actionable business insights.
Identify use-case-specific data sources and design robust methods for data collection, integration, cleansing, and transformation in collaboration with data engineers.
Partner with software engineering teams to integrate GenAI components into existing platforms, ensuring seamless communication and compatibility across software modules.
Enforce ethical AI practices (fairness, transparency, and accountability) by actively identifying and mitigating biases or risks prior to deployment.
Conduct proactive research and POC experimentation on the latest advancements in GenAI technologies, frameworks, and algorithms to continuously enhance Enterprise AI capabilities.
Evaluate and benchmark emerging GenAI models while providing technical guidance, code reviews, and mentorship to development team members.
Align and support the overall organization's GenAI strategy and technology adoption roadmap.