AI Solutions Architect (Hands-On LLM / RAG Systems)
Role details
Job location
Tech stack
Job description
We are seeking a highly technical AI Solutions Architect to lead the development and delivery of enterprise-grade AI applications. This role is focused on building and owning full-cycle AI systems, transforming business challenges into scalable, production-ready solutions.
Rather than concentrating on analytics or strategy, this position is deeply hands-on-requiring expertise in designing architectures, developing applications, and deploying reliable AI systems integrated directly into core business workflows.
The ideal candidate will play a critical role in advancing AI maturity by moving initiatives beyond experimentation into stable, production-level implementations that drive measurable business impact.
Responsibilities
- Architect, develop, and deploy end-to-end AI solutions for business use cases
- Build and implement LLM-powered applications, including RAG pipelines and agent-based systems
- Write and maintain production-quality code primarily in Python
- Integrate AI solutions with enterprise platforms such as ERP, HRIS, and collaboration tools
- Ensure system performance, scalability, and reliability in live environments
- Optimize solutions for efficiency, accuracy, and cost control
- Lead the transition from proof-of-concept models to fully operational production systems
- Own lifecycle management including monitoring, iteration, and continuous improvement
Requirements
- Strong experience with Large Language Models (LLMs) and real-world applications
- Hands-on expertise building RAG (Retrieval-Augmented Generation) pipelines
- Experience with vector databases (e.g., Pinecone, FAISS, Weaviate, Chroma)
- Advanced proficiency in Python development
- Proven ability to design, build, and deploy production-grade AI systems
- Experience integrating AI solutions into enterprise environments
- Deep understanding of system architecture, scalability, and deployment practices
- Track record of delivering end-to-end AI implementations in production