Lead AI Engineer - Agentic Solutions

Beyond is Qodea’s Customer Experience Design Studio.

We design the ‘surfaces’ where customers and technology meet.

Our teams shape the intelligence behind those experiences, turning data, design, and emerging technologies into products that are intuitive, adaptive, and human.

We are multi-disciplinary designers, product strategists, writers, architects, engineers, data scientists, and ML researchers, united by a single goal: to design a better future for our clients and their customers.

We believe we are on the cusp of a new golden era of design, one where design will be more important than ever.  An era of exploration and discovery.

We’re building a studio where designers immerse themselves in AI design paradigms, experimenting with adaptive patterns, conversational interfaces, and agentic workflows, the foundation for tomorrow’s customer experience.

We look for people who embody:

Innovation to solve the hardest problems.

‍Accountability for every result.

‍Integrity always.

About The Role:

• We are seeking a driven, experienced technical leader to define and scale the next generation of intelligent, multi-agent solutions. This role is central to building high-traffic, commercial-grade platforms that blend conversational user experiences with autonomous, transactional workflows.

• The successful candidate will be responsible for the end-to-end architecture and operationalization of these systems, ensuring they are secure, highly available, and capable of handling millions of users. You will be the technical authority for agentic design, guardrails, and continuous evaluation, setting the bar for excellence in a rapidly evolving field.

What You'll Do:

• Lead Agent Architecture: Architect, design, and deploy scalable, multi-agent systems for high-traffic environments, leveraging frameworks such as Google's ADK (Agent Development Kit), LangGraph, CrewAI, or similar graph-based and role-based orchestration tools.
• Implement High-Performance Pipelines: Design and build the underlying service architecture, utilizing Python or Go to ensure low-latency and high-concurrency for blended conversational and transactional flows.
• Manage Agent Memory and Knowledge: Implement advanced short-term memory (session state) and long-term memory management, including integrating and maintaining Vector Data Stores (e.g., Google Cloud Vector Search) for efficient information retrieval (insert/extract).
• Drive Retrieval Strategy: Design and implement robust RAG (Retrieval Augmented Generation) and RAGGraph strategies to ground agents in trusted enterprise knowledge, ensuring factual accuracy and reducing hallucination.
• Tool Integration and Extensibility: Define and implement mechanisms to extend agent functionality by integrating with external APIs and services (Tools), including systems via MCP (Multi-Cloud Platform) servers or similar gateways.
• Establish Reliability and Guardrails: Design, implement, and maintain observability, logging, and security guardrail frameworks to guarantee the correctness, safety, and compliance of agent behaviors in production.
• Define Evaluation Frameworks: Create and industrialize automated evaluation frameworks that measure business outcomes (e.g., resolution time), technical reliability (latency, error handling), and the agent’s reasoning/tool-use correctness against defined rubrics.
• Develop robust data pipelines: Build data ingestion, transformation, and export pipelines to create high-quality training datasets.
• Automate Deployment: Design, implement, and maintain CI/CD pipelines to enable continuous integration and automated deployment of the agents, their correlated cloud components, and infrastructure-as-code configurations.
• Champion Best Practices: Act as a technical leader, mentoring engineering peers and championing engineering best practices around system design, documentation, and continuous delivery within a cloud-native environment.

Requirements:

• Experience: 8+ years in software, AI/ML, or systems engineering, with a minimum of 3 years directly designing and deploying LLM solutions or LLM-based, multi-agent systems at scale.
• Architecture and Scale: Proven experience designing and operating high-throughput, distributed backend systems in cloud environments (GCP), utilizing Kubernetes, Docker, and service meshes.
• LLM Orchestration Mastery: Deep hands-on experience with modern agent orchestration frameworks (LangGraph, Google ADK, CrewAI) and core AI techniques like ReAct (Reasoning and Acting), Plan-and-Execute, and prompt engineering for autonomous agents.
• MLOps & DevOps: Demonstrable expertise in building and maintaining CI/CD pipelines (e.g., Jenkins, GitLab CI, Cloud Build) for deploying and versioning machine learning models and serverless components.
• Data and Memory: Expert knowledge of data modeling and integrating vector stores (e.g., Pinecone, ElasticSearch, Vertex AI Vector Search) for high-performance retrieval and entity-aware long-term memory.
• Cloud Ecosystem Focus: Strong hands-on experience with the Google Cloud Platform ecosystem, including Vertex AI (Generative AI Studio, Models), BigQuery, and Cloud Run/Functions for deployment.
• Software Engineering: Mastery of Python and/or Go for production-grade development, including building robust APIs (REST/gRPC) and implementing CI/CD pipelines.
• Leadership and Alignment: Proven ability to influence technical direction across multiple teams and align diverse stakeholders (ML, Product, Security) around a cohesive agentic vision.

Preferred Qualifications:

• Experience with Federated Learning or techniques for maintaining agent policy consistency across decentralized environments.
• Familiarity with compliance and governance frameworks for AI (e.g., AI Act, industry-specific standards) relevant to highly regulated domains (e-commerce, financial services).
• Active participation in the open-source community for agentic frameworks or LLM operations.

Diversity and Inclusion

At Beyond, we champion diversity and inclusion. We believe that a career in IT should be open to everyone, regardless of race, ethnicity, gender, age, sexual orientation, disability, or neurotype. We value the unique talents and perspectives that each individual brings to our team, and we strive to create a fair and accessible hiring process for all.