AI Architect

We’re not just building better tech. We’re rewriting how data moves and what the world can do with it. With Confluent, data doesn’t sit still. Our platform puts information in motion, streaming in near real-time so companies can react faster, build smarter, and deliver experiences as dynamic as the world around them.

It takes a certain kind of person to join this team. Those who ask hard questions, give honest feedback, and show up for each other. No egos, no solo acts. Just smart, curious humans pushing toward something bigger, together.

One Confluent. One Team. One Data Streaming Platform.

The Business Systems team manages the backbone of our company’s operations. We oversee the core platforms that drive our business: Salesforce, NetSuite, and Zendesk. Our goal is to modernize this stack by integrating practical AI solutions that automate manual workflows and improve data accessibility for our internal teams

We are looking for a hands-on AI Architect to deliver technical designs and implementations of internal AI tools.

This is a hybrid role where you will act as a software architect, a lead engineer, and a technical partner to the business. You will be responsible for taking vague business problems and turning them into reliable, secure AI software solutions. You will be instrumental in defining the architecture and writing the code that runs in production.

System Architecture & Integration

• Design for Action: Build AI integrations that do more than just summarize text. Design systems that can securely read from and write back to our core platforms (e.g., updating a record in Salesforce or drafting a response in Zendesk).

• Secure Data Flow: Architect the integration layer between external LLM providers (Google, Anthropic, OpenAI) and internal data. Ensure all data retrieval is governed by strict permissions so users are only able to access data they are authorized to see.

• Scalability: Design a model-agnostic inference layer that allows us to switch between models based on performance and cost requirements.

Hands-On Development

• Backend Engineering: Write production-ready code using modern agent frameworks (ADK, LangChain). This is a technical role that requires coding.

• Retrieval Augmented Generation (RAG): Implement robust RAG pipelines to ground AI responses in company data. This includes managing vector databases and optimizing search strategies (hybrid search, reranking) to ensure accuracy.

• Deployment: Set up the CI/CD pipelines and infrastructure required to deploy and maintain these services in a cloud environment.

Quality & Governance

• Evaluation: Move beyond "eye-balling" results. Implement automated testing frameworks to measure response accuracy, latency, and costs before deploying changes.

• Data Privacy: Ensure strict handling of PII and adherence to enterprise security standards. You will be the gatekeeper for how sensitive data is exposed to LLMs.

Stakeholder Partnership

• Requirements Gathering: Partner with leaders in Sales, Marketing, and Support to identify high-impact automation opportunities. Translate business needs into technical specifications.

Technical Experience:

• Software Engineering: 8+ years of experience in software development with strong proficiency in Python and API design (REST).

• Applied AI: 2+ years of experience building LLM-powered applications or agents (using libraries like LangChain or ADK).

• Data Engineering: Experience with Vector Databases (e.g., Pinecone, pgvector) and building pipelines to process unstructured text.

• Cloud Infrastructure: Hands-on experience deploying services on AWS, Azure, or GCP.

Integration & Business Skills:

• Enterprise Platforms: Proven experience integrating custom applications with SaaS platforms like Salesforce, NetSuite, or Zendesk. You understand their data models and API constraints.

• Communication: Ability to explain technical concepts to non-technical stakeholders and collaborate effectively with product managers and business analysts.

• Hands-on experience with GCP Vertex AI features and technologies (Agent Engine, RAG Engine etc)

Belonging isn’t a perk here. It’s the baseline. We work across time zones and backgrounds, knowing the best ideas come from different perspectives. And we make space for everyone to lead, grow, and challenge what’s possible.

We’re proud to be an equal opportunity workplace. Employment decisions are based on job-related criteria, without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, veteran status, or any other classification protected by law.