RAG Arcitect/Engineer
Overview:
In this role you will design and scale enterprise-grade GenAI RAG solutions, working across product, software, and data teams to translate complex business needs into robust GenAI infrastructure. You will lead architectural decisions, optimize LLM-based systems, and drive data integration and ethical AI practices. The position blends hands-on development with technical leadership, shaping GenAI capabilities for enterprise-scale problems. A key hook is advancing a scalable AI platform within a global technology services leader. Compensation / Benefitsremote or hybrid work optionsflexible work arrangementsopportunity to impact enterprise AI strategycollaboration with cross-functional teamsgrowth and learning in cutting-edge GenAI techemployer commitment to responsible AI practices
Responsibilities:
- Design and optimize vector database foundations to support LLMs across enterprise GenAI tools
- Architect and scale GenAI infrastructure including storage, processing, and high-performance retrieval
- Lead architectural decisions with external GenAI providers (e.g., Azure, AWS) for scalability and cost-efficiency
- Collaborate with business partners, product owners, and engineers to convert requirements into enterprise GenAI solutions
- Drive model optimization and fine-tuning for LLMs to improve performance and throughput
- Present architectural designs and analyses to non-technical stakeholders
- Identify data sources and design robust data collection, integration, cleansing, and transformation methods
- Partner with software teams to integrate GenAI components across platforms
- Enforce ethical AI practices by identifying and mitigating biases and risks
- Conduct R&D and POC on latest GenAI technologies to enhance enterprise capabilities
- Provide guidance, code reviews, and mentorship to the development team
- Align with the organization's GenAI strategy and adoption roadmap
Key requirements:
5+ years building and deploying enterprise AI applications Advanced understanding of LLMs, NLP, and AI agents with RAG architectures 3+ years using pre-trained language models via APIs or frameworks like Hugging Face 3+ years with NLP libraries (NLTK, SpaCy, Gensim, BERT, SBERT) and orchestration frameworks (LangChain, LangGraph, EmbedChain)5+ years Python experience or equivalent Bachelor's degree in Computer Science, Data Science, or equivalent practical work experience Effective collaboration with cross-functional teams Strong communication for both technical and business audiences Mentorship and coaching of engineers GenAI and RAG architecturesLLMs and NLP fundamentals LangChain/LangGraph/EmbedChain