Hybrid GenAI Solutions Architect

at Power Factors

• Job title: GenAI Solutions Architect
• Job type: Full Time
• Experience level: Mid level, Senior
• Salary: Not specified
• Degree requirement: Bachelor's Degree
• Tech skills: AWS, Azure, Cloud, Docker, ETL, Google Cloud Platform, Java, Kubernetes, Microservices, Python, TypeScript
• Location requirements: Hybrid, Athens, Greece

About the role

• Software Engineer deploying enterprise-grade Generative AI solutions at Power Factors, a clean energy software provider. Balancing AI capability development and governance across product teams.

Responsibilities

• Build owned AI capabilities (40-50% of time): Work within the GenAI team to design, develop, and operate specific GenAI features and shared services that are owned by our team. Contribute to our product roadmap, participate in sprint ceremonies, and deliver production-grade AI capabilities that serve as reference implementations for the broader organization.
• Embed & govern with product teams (40-50% of time): Rotate across product engineering teams as the technical representative of our team and AI steering committee, joining each squad for 1–3 sprints (typically working with 4–6 teams per year). You'll ensure proposed solutions align with enterprise architectural standards, leverage shared patterns and services our team has developed, and incorporate latest GenAI best practices. You'll review designs for compliance, identify reuse opportunities, prevent redundant builds, and guide teams toward approaches that support long-term maintainability and cross-team consistency.
• Architect production-grade solutions: Design and implement LLM patterns (e.g., RAG, finetuning, function/tool calling, agent workflows). Select models/services (e.g., Azure OpenAI, OpenAI, AWS Bedrock, Vertex AI) and integrate with existing microservices and data platforms.
• Data & retrieval: Build high quality retrieval pipelines (document chunking, metadata strategy, hybrid search) and manage vector stores for accuracy, coverage, and freshness.
• Quality, safety & governance: Establish evaluation pipelines (automatic and human-in-the-loop), prompt/version management, guardrails, incident playbooks, and Responsible AI controls (privacy, bias, safety).
• Performance & cost optimization: Instrument telemetry, monitor latency/quality, apply caching/streaming/batching, and manage token budgets to meet SLAs and reduce spend.
• Maintain technology radar: Stay current with the rapidly evolving GenAI landscape, evaluate new models/frameworks/patterns, and work with the steering committee to update enterprise standards. Ensure teams benefit from latest advancements without architectural chaos.
• Enable & upskill: Create reusable reference architectures, prompt libraries, SDKs/components (e.g., Semantic Kernel or LangChain), and run workshops/pairing sessions to elevate team capability.

Requirements

• Experience: 5+ years building ML/AI or data intensive software; demonstrated experience of delivering LLM solutions in an enterprise grade software (not just prototypes).
• Engineering: Strong coding in Python and one of TypeScript/Java; API/microservices, CI/CD, testing, containerization (Docker/Kubernetes).
• Cloud & data: Experience with Azure/AWS/GCP, ETL/ELT, data modeling, and data quality practices.
• LLM/GenAI: Practical knowledge of embeddings, prompt engineering, RAG, tool/agent frameworks, evaluation methods.
• Consulting skills: Excellent stakeholder management, facilitation, and change-management; clear written/verbal communication to technical and non-technical audiences.