Principal AI Architect

Key Responsibilities

Architect, design, and evolve a scalable, secure AI platform and reference architecture that enables rapid development of AI‑powered product capabilities.

Drive strategic decision‑making across Model selection and fine‑tuning, Retrieval‑Augmented Generation (RAG) Agent frameworks, Data pipelines, and Inference optimization.

• Evaluate and integrate Open‑source and commercial LLMs, Vector databases, Feature stores, MLOps platforms.
• Collaborate cross‑functionally with Product, Engineering, Architecture, and UX to define AI requirements and priorities.
• Lead and influence engineering teams, fostering a culture of innovation and architectural excellence.
• Lead architecture reviews, technical governance, and long‑term platform planning.

Provide architectural direction for Agentic AI systems, including:
Workflow orchestration, Multi‑agent collaboration, Context management, Safety controls, Autonomous decision‑making frameworks.

Design and implement LLMOps and AIOps practices for production systems. Drive observability practices for monitoring agent behavior and system performance.

• Define guardrails for Agent interactions, Memory usage, Context boundaries, Governance & Standards.
• Define and enforce target‑state architectures, principles and standards for AI/ML Responsible AI and ethical frameworks (e.g., GDPR, NIST AI RMF).
• Establish processes for metadata extraction and management, enabling granular access control.

• 8+ years of experience as a Senior, Lead, or Principal Engineer/Architect.
• Hands‑on experience with AI and ML systems in production environments.
• Proven ability to lead large‑scale architectural initiatives and influence cross‑functional decisions.

• Strong programming proficiency in Python (expert‑level required), Java, Type Script, Node.js, or similar.
• Experience with AI frameworks such as Lang Graph, Lang Chain, Llama Index, Semantic Kernel, Auto Gen.
• Deep experience with Large Language Models (LLMs), Embeddings, Vector databases, RAG architectures, Model serving frameworks.
• Hands‑on experience with Agentic AI patterns, including Autonomous agents, Tool usage, Multi‑agent coordination, Goal‑directed planning.
• Strong background in cloud platforms (AWS, Azure, or GCP), Containerization, Serverless technologies, Distributed systems, Security & Systems Design.
• Experience designing secure AI systems, including data privacy, encryption, compliance, Responsible AI practices.
• Solid understanding of API integration patterns, Messaging systems, Event‑driven architectures, Modern Architecture, Microservices architectures, Domain‑driven design (DDD), Platform engineering, scalable distributed systems.

• Proven leadership experience.
• Excellent communication, problem‑solving, and technical leadership skills.
• Ability to influence and align teams across organizational boundaries.

Tricentis is proud to be an equal opportunity workplace.
Qualified applicants will receive consideration for employment without regard to race, color, ethnicity, gender, religious affiliation, age, sexual orientation, socioeconomic status, or physical and mental disability and other statuses protected by law.