AI Architect – Generative AI Solutions

About the role

PwC is hiring an AI Architect in Sofia to design and guide production-ready Generative AI solutions for clients, from early discovery through implementation. The role combines hands-on architecture, technical leadership and client collaboration, helping teams choose where Generative AI adds value, build secure and scalable solutions and measure quality and cost in production.

Key responsibilities

• Lead the architecture and delivery of Generative AI solutions, guiding development teams on tools, frameworks and platforms
• Translate business requirements into application, service and target-state architectures, including reusable RAG, agent orchestration, prompt and evaluation patterns
• Own scalability, performance, latency, observability, security and cost optimisation
• Lead technical design and code reviews, and define the right adaptation approach (prompting, RAG, fine-tuning, distillation)
• Own evaluation strategy, including golden datasets, offline and online evaluation, human-calibrated LLM-as-judge and CI regression testing
• Set retrieval quality standards and define AI security, privacy, responsible AI and governance controls
• Own solution economics through model routing, caching, batching and capacity planning
• Supervise vendor developers, mentor engineers and junior architects, and support business development

Required profile

• 5+ years of experience in agile product delivery
• Hands-on experience designing and delivering production software solutions at scale
• Demonstrated expertise in Generative AI solution architecture, with at least one Generative AI system delivered to production
• Bachelor's or Master's degree in Computer Science or Engineering, or equivalent practical experience
• Fluent written and spoken English

Required skills

• Generative AI and agent architecture: large language models, RAG, agent orchestration, vector search and retrieval, production AI agents, structured generation
• Azure cloud architecture, microservices, containers (Docker/Kubernetes), CI/CD and DevOps tools
• LLMOps, observability and AI security (OWASP Top 10 for LLM applications)
• Preferred: Azure certification, Model Context Protocol, fine-tuning, multimodal AI, EU AI Act and ISO/IEC 42001 knowledge, consulting experience

What we offer

• Work with local and international clients and the global PwC network
• Technical training, coaching and support for professional qualifications
• Hybrid working and a modern office in central Sofia
• 25 days of annual leave, health insurance, meal vouchers, Multisport card and fringe benefits
• Career growth opportunities

The selection process includes a case study, a technical interview and a final interview.