LLM & RAG Solutions Architect

Description:

The LLM & RAG Solutions Architect at BlackStone eIT will be responsible for designing and implementing solutions that leverage Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) techniques. This role focuses on creating innovative solutions that enhance data retrieval, natural language processing, and information delivery for our clients.

Responsibilities:

• Develop architectures that incorporate LLM and RAG technologies to improve client solutions.

• Collaborate with data scientists, engineers, and business stakeholders to understand requirements and translate them into effective technical solutions.

• Design and implement workflows that integrate LLMs with existing data sources for enhanced information retrieval.

• Evaluate and select appropriate tools and frameworks for building and deploying LLM and RAG solutions.

• Conduct research on emerging trends in LLMs and RAG to inform architectural decisions.

• Ensure the scalability, security, and performance of LLM and RAG implementations.

• Provide technical leadership and mentorship to development teams in LLM and RAG best practices.

• Develop and maintain comprehensive documentation on solution architectures, workflows, and processes.

• Engage with clients to communicate technical strategies and educate them on the benefits of LLM and RAG.

• Monitor and troubleshoot implementations to ensure optimal operation and address any arising issues.

Requirements

Resource Requirement – AI/Multi-Agent Chatbot Architect (RAG & On-Prem LLM)

We are looking to onboard a specialized technical resource with the following expertise:

• Proven Experience in Multi-Agent Chatbot Architectures:
  Hands-on experience designing and implementing multi-agent conversational systems that allow for scalable, modular interaction handling.
• On-Premise LLM Integration:
  Demonstrated capability in deploying and integrating large language models (LLMs) in on-premise environments, ensuring data security and compliance.
• RAG (Retrieval-Augmented Generation) Implementation:
  Prior experience in successfully implementing RAG pipelines, including knowledge of embedding strategies, vector databases, document chunking, and query optimization.
• RAG Optimization:
  Deep understanding of optimizing RAG systems for performance and relevance, including latency reduction, caching strategies, embedding quality improvements, and hybrid retrieval techniques.

Optional but preferred:

• Familiarity with open-source LLMs (e.g., LLaMA, Qwen, Mistral, Falcon)
• Experience with vector DBs such as VectorDB, FAISS, Weaviate, Qdrant, etc.
• Workflow orchestration using frameworks like LangChain, LlamaIndex, Haystack, etc.

Benefits

• Paid Time Off
• Performance Bonus
• Training & Development