Technical AI Architect & Builder

At NiCE, we don’t limit our challenges. We challenge our limits. Always. We’re ambitious. We’re game changers. And we play to win. We set the highest standards and execute beyond them. And if you’re like us, we can offer you the ultimate career opportunity that will light a fire within you.

As Senior Technical AI Architect & Builder, you will set the technical direction for SPARK and build alongside the team. You will advise on the tech stack, choose the patterns and tools we standardize on, and write the code for flagship prototypes yourself. You will also advise business and technology leaders on what is feasible, what is wise, and what to build next.

This is a consultative and autonomous role. You are comfortable owning ambiguous problems end to end, making sound technical decisions with minimal supervision, and explaining your reasoning to engineers and executives alike. You will be the senior technical lead for the SPARK AI Architects & Builders.

How will you make an impact?:

• You will own the technical architecture of SPARK and the quality of what it ships, from the first prototype to the enterprise-grade tool, working hands-on with the Technical AI Architect & Builder, the Business Analyst, and NiCE’s platform, security, and architecture teams.

Set Technical Direction:

• Recommend and own the SPARK tech stack: models and providers, agent and orchestration frameworks, retrieval and vector storage, integration patterns, and developer tooling
• Make build-versus-buy and platform-versus-custom decisions, and record them in clear architecture decision records
• Define reference architectures and reusable patterns so every new idea starts from a paved path instead of a blank page
• Track the fast-moving AI landscape and bring forward the models, tools, and protocols worth adopting
• Ensure build allows tools to be migrated easily
• Always ensure cost optimization is included in the design

Build Hands-On:

• Design and build agentic AI solutions, including tool use, multi-step reasoning, memory, multi-agent coordination, and human-in-the-loop controls
• Build RAG pipelines and integrations with enterprise systems such as Salesforce, ServiceNow, Workday, and Microsoft 365, using APIs and MCP
• Ensure solution design incorporates NiCE guidelines on ethics, risk, and compliance
• Review data and infrastructure readiness of the solutions
• Write clean, tested, documented code that others can pick up and extend
• Turn ideas into working prototypes quickly, and into demonstrable value for the business teams who proposed them

Take Prototypes to Enterprise Grade:

• Define what enterprise-grade means for SPARK: security, access control, privacy, reliability, scalability, observability, and cost
• Harden prototypes for global rollout, including CI/CD, automated tests, evaluation pipelines, monitoring, and rollback
• Establish LLM evaluation practices: test sets, regression tests, hallucination checks, and quality dashboards
• Work with Security, Legal, and Architecture teams to embed responsible AI and data protection requirements into every design

Advise and Lead:

• Act as trusted technical adviser to business teams, the Project Manager, and senior leaders on feasibility, trade-offs, effort, and risk
• Review designs and code, mentor the Technical AI Architect & Builder, and raise the engineering bar across the team
• Work with minimal supervision, flag risks early, and make good decisions when requirements are still moving
• Collaborate with NiCE’s internal and external AI platform and architecture teams so SPARK solutions fit the wider enterprise AI strategy

Have you got what it takes?:

• Bachelor’s degree in Computer Science, Software Engineering, or a related field (Master’s preferred), or equivalent experience
• 10+ years of software engineering experience, including 3+ years designing and delivering LLM-powered or agentic AI systems in production
• Expert, hands-on skills in Python and/or TypeScript; you are still a developer who writes code every week
• Deep experience with agent and orchestration frameworks (such as LangGraph, LangChain, AutoGen, or equivalent), tool-integration protocols such as MCP, and RAG architectures with vector databases
• Strong working knowledge of LLM providers and APIs (Anthropic Claude, OpenAI, Azure OpenAI, Gemini, and open-source models), including prompt design, structured outputs, and evaluation
• Experience with at least one major cloud AI ecosystem (Azure, AWS, or GCP) and with REST API, event-driven, and microservice design
• Strong grasp of security, privacy, and responsible AI practices for enterprise systems
• Proven ability to work independently, advise stakeholders, and own technical decisions in ambiguous situations
• Excellent communication skills, with the ability to explain complex AI concepts to executives and non-technical colleagues
• Fluency in English

You will have an advantage if you also have:

• Experience in an AI center of excellence, innovation lab, or internal incubator
• Experience with Cognigy, NiCE CXone, or other CCaaS and conversational AI platforms, including voice AI
• Experience integrating with enterprise systems such as Salesforce, ServiceNow, Workday, Atlassian, and Microsoft 365
• Experience with LLMOps: evaluation frameworks, observability (OpenTelemetry), prompt registries, and cost governance
• Experience fine-tuning or evaluating open-source models
• Experience with workflow applications such as N8N or similar
• Have developed market-ready software applications
• Fluency in a foreign language; German would be a plus, for close collaboration with the Forward Deployment Cognigy team in Germany

Skills

AWS, AutoGen, Azure, GCP, LangChain, LangGraph, MCP, Python, RAG, TypeScript