Senior AI Engineer

Senior AI Engineer, Multi-Agent Systems

Shape the Future of Marketing Intelligence with Alphix

At Alphix, we’re redefining what’s possible in marketing performance and activation. As part of Fundamental Group, an established and trusted name in media intelligence, Alphix operates with the speed, mindset and energy of a start-up, constantly experimenting, innovating, and deploying powerful solutions. We are now fundamentally changing our approach, moving our data exploration and insights from a traditional web application to a fully agentic experience.

We're looking for an exceptional Senior AI Engineer who will take the lead on this ambitious project. You will be a hands-on leader, spearheading our multi-agent system capabilities and shaping our entire AI architecture to deliver next-level insights and automation.

What You'll Be Doing

• Lead the vision and execution of our multi-agent system from initial exploration and prototyping to a production-ready, scalable service.
• Design and orchestrate agentic workflows and architectures, defining the roles, communication protocols, and task delegation for specialized LLM agents.
• Build the core LLM-powered services that agents will use, including advanced RAG (Retrieval-Augmented Generation) pipelines, custom model tuning, and semantic insights.
• Design and build vector database solutions for scalable semantic search, contextual analysis, and real-time decision-making.
• Collaborate cross-functionally with product and engineering teams to integrate agentic solutions seamlessly into our core product, with real users and measurable impact.
• Champion ML best practices, robust MLOps pipelines, and high-quality model monitoring for our new agentic architecture.
• Constantly explore emerging tools and research new LLM techniques to ensure we are at the forefront of the industry.

Our Technology Stack

You'll be working at the intersection of cutting-edge AI and robust, scalable cloud infrastructure. We are building our next-generation platform on a modern stack, and your expertise will be crucial in leveraging these tools to their full potential.

Our agentic architecture will be built on powerful frameworks like LangChain and LangGraph, which we are exploring for their advanced state management and cyclical graph capabilities. We are also evaluating other leading tools like AutoGen and CrewAI to orchestrate seamless collaboration and decision-making between our agents.

The core intelligence for our agents will be powered by a diverse range of Large Language Models (LLMs), chosen based on the specific needs of each application. This includes using models like Google's Gemini Models via Vertex AI, as well as other leading API-based models. In addition, you will be responsible for deploying and managing self-hosted models to meet specific performance, security, and cost requirements. You will be responsible for deploying these services using Google Kubernetes Engine (GKE) for our scalable, containerized solutions, and leveraging Cloud Run and Cloud Functions for serverless, event-driven microservices.

A key part of the agent's power will come from its ability to access and utilize a vast knowledge base. We will be using SingleStore, our existing high-performance database, as the central hub for both our relational and vector data, eliminating the need to manage a separate vector database. You will use its native vector search capabilities to build and optimize our RAG (Retrieval-Augmented Generation) pipelines. For unstructured data and large artifacts, we will rely on GCP Cloud Storage.

Finally, we believe in building for production from day one. You will champion robust MLOps practices, using Vertex AI for model management and Google Cloud Logging / Cloud Monitoring for observability. We also plan to use LangSmith to monitor, evaluate, and debug our complex agentic workflows, ensuring high performance and reliability.

About You

• You are a creative builder and a technical leader, excited by the chance to develop intelligent systems that didn't exist before and to guide others in that journey.
• Deep, hands-on experience with:
• Building and orchestrating multi-agent systems.
• LLM application stacks (RAG pipelines, prompt engineering, model evaluation).
• Vector databases and their application in production environments.
• Deployment of complex AI/ML models at scale.
• You’ve led the development and deployment of AI/ML solutions that had real, measurable impact for clients or internal users, and you can talk us through them.
• You have a strong foundation in machine learning, NLP, data engineering, and model architecture.
• Curious, collaborative, and self-directed, you thrive in environments where ambiguity is an opportunity for groundbreaking work.
• You care about user experience and business outcomes as much as you do about algorithmic elegance.

Why Join Alphix?

• Pioneer a new paradigm: We are building the next generation of marketing intelligence from first principles, transitioning from a static web app to a dynamic, agentic experience.
• Lead a team, own your impact: Your work will define the core of our next-gen product, drive our product roadmap, and give you the opportunity to lead in a fast-paced environment.
• Innovation at speed: We move fast, test ambitiously, and keep learning. Expect hackathons, prototypes, and quick wins, balanced with big thinking and long-term vision.
• Support + stability: As part of Fundamental Group, you get the best of both worlds—start-up freedom with enterprise backing.

Ready to Build with Us?

If you're passionate about solving tough problems with smart code, deploying AI with real-world value, and pushing boundaries in an ambitious, supportive team, we want to hear from you.

Apply now or reach out to our team with examples of your work, side projects, or anything else you think showcases your capabilities.