Senior AI Solutions Architect with LLM and RAG

Project Overview

This project focuses on building a scalable AI platform that transforms expert knowledge into structured graph-based intelligence and connects it with enterprise-grade language models. The solution emphasizes semantic search, agent workflows, and robust evaluation frameworks to ensure reliable outputs.

Position Overview

We are looking for a Senior AI Solutions Architect to lead the design and implementation of advanced LLM-driven solutions with a strong focus on retrieval-augmented generation and knowledge graph integration. You will take ownership of the full orchestration layer, shaping how structured and unstructured data is transformed into high-quality, context-aware AI responses.

Technology Stack

• Python
• SQL
• Vector databases
• Graph databases
• Google Cloud Platform
• Cloud Spanner
• Vertex AI
• Gemini
• LLM frameworks
• Embedding models
• Observability tools
• IAM
• Encryption

Responsibilities

• Design and manage end-to-end LLM orchestration and retrieval pipelines
• Define embedding model selection and chunking strategies, including context window management and trade-offs affecting retrieval quality and cost
• Own the entity extraction pipeline to convert unstructured content into graph nodes and relationships
• Implement entity resolution, relationship normalization, and deduplication processes
• Design and refine semantic search strategies and retrieval logic across graph and vector layers
• Develop prompt engineering approaches and agentic workflows for advanced use cases
• Integrate graph-based outputs with enterprise AI platforms such as Gemini
• Design and maintain evaluation frameworks including ground truth dataset creation
• Measure and improve retrieval quality using metrics such as recall, precision at K, faithfulness, and answer relevance
• Establish systematic regression testing practices for AI pipelines
• Optimize LLM usage costs across the full retrieval and generation lifecycle
• Implement observability, logging, and tracing to monitor performance and reliability

Requirements

• Experience designing and implementing LLM-based systems in production environments
• Hands-on experience with retrieval-augmented generation and semantic search
• Strong understanding of embeddings, vector search, and chunking strategies
• Experience building entity extraction pipelines and working with knowledge graphs
• Proficiency in Python and data processing workflows
• Understanding of prompt engineering and agent workflow design
• Experience defining evaluation frameworks and quality metrics for AI systems
• Familiarity with distributed systems and scalable data architectures
• Experience implementing observability, logging, and tracing in data-intensive environments

Nice to Have

• Experience with Google Cloud Platform services including Cloud Spanner and Vertex AI
• Familiarity with enterprise AI platforms such as Gemini
• Knowledge of cost optimization techniques for large-scale LLM systems
• Experience with graph data models and hybrid architectures combining graph, relational, and vector data
• Exposure to advanced evaluation techniques for generative AI and ranking systems

What We Offer

• Vacation days: Up to 26 business days per year
• 10 illness/special days off per year (fully paid, no medical papers needed) for all contract types
• Health and life insurance (Luxmed)
• MyBenefit platform with Multisport option
• Internal psychological support service
• English language classes from the first working day
• Access to external learning platforms: O’Reilly, LinkedIn Learning, Udemy, and a wide catalog of diverse internal training
• Flexible workplace: work from the office, from home, or choose a hybrid option
• Tech Skills Mentoring Program
• Opportunities to develop as a public speaker, mentor, or technical interviewer
• Fully paid idle (bench) when not involved in a project
• Certification reimbursement (AWS, GCP, Microsoft, etc.)