The Agentic Solutions Engineer will join the AI Platform team within the CIB ITO Industrial Transformation division at BNP Paribas. This role is central to the bank's strategic initiative to deploy AI Agents across global operations by 2030. The primary mission is to bridge the gap between advanced AI capabilities and business implementation, leading the 'Agentic Bootstrap' initiative to help project teams structure requirements and adopt agentic frameworks. Responsibilities include evangelizing the internal Agentic Framework, providing hands-on technical guidance to project teams, and contributing to the continuous evolution of the framework based on field feedback. Candidates must possess strong theoretical and practical knowledge of LLMs and a proven track record in deploying AI solutions using frameworks like LangGraph and Google AI SDK. The role requires an ability to design scalable, robust AI architectures and a unique blend of technical depth and interpersonal agility. Required qualifications include an Engineering or equivalent degree with at least 8 years of relevant experience. Behavioral competencies such as analytical synthesis, adaptability, proactive curiosity, and a collaborative mindset are essential for navigating this complex, multi-disciplinary environment.
For full details about this role, click “Apply on company site” to view the employer’s original posting.
Skills for this role
Large Language Models (LLMs)Generative AI FrameworksAgentic OrchestrationLangGraphGoogle AI SDKFact MCPSTTArizeDynatraceDockerKubernetesApplication DesignTechnical Formalization
Your skill match
Checking your profile…
YOUR NEXT STEP
Get interview-ready for this role
A focused preparation guide, built around this job’s responsibilities and requirements.
✦ AI-generated guide
Preparation suggestions, not the employer’s actual interview questions. Always check the original posting for current requirements.
01
Understand the role
What matters most
Leading the Agentic Bootstrap Initiative
The core mission is to bridge the gap between advanced AI capabilities and business implementation. You must be able to guide diverse project teams through the process of structuring requirements and adopting the internal Agentic Framework to ensure production-ready deployments.
Technical Evangelism and Framework Evolution
You are responsible for communicating the roadmap and best practices of the Agentic Framework across the CIB division. This requires gathering field feedback from project teams to iteratively improve the framework's features and optimizations.
Architecting Scalable AI Solutions
You must design robust, scalable AI architectures using tools like LangGraph and Google AI SDK. The role demands a high level of technical depth to ensure that autonomous intelligence solutions meet the industrial-grade standards required for global banking operations.
Likely challenges to think through
Navigating Complex Stakeholder Environments
As a bridge between technical AI teams and business units, you will face the challenge of translating complex technical requirements into actionable solutions for non-technical stakeholders. Prepare by demonstrating your ability to synthesize information and communicate technical impact clearly.
Balancing Standardization with Project Customization
The 'Agentic Bootstrap' initiative requires ensuring project teams adhere to AI Platform standards while allowing for the flexibility needed for unique business use cases. Prepare by discussing how you manage technical governance without stifling innovation or project velocity.
Adapting to Rapidly Evolving AI Frameworks
The field of agentic orchestration is moving quickly, and you are expected to stay ahead of the curve while maintaining production stability. Prepare by highlighting your process for continuous learning and how you evaluate new technologies for integration into an existing enterprise framework.
03
Practice your answers
Technical practice
Designing Scalable Agentic Architectures
What to coverExplain how you would design a robust, production-ready AI agent architecture using LangGraph. Focus on handling state management, error recovery, and ensuring scalability within a large enterprise environment.
LLM Framework Implementation Trade-offs
What to coverCompare the use of LangGraph versus other orchestration frameworks for complex, multi-step agentic workflows. Discuss how you evaluate which framework best fits specific business requirements.
Monitoring and Observability for AI Agents
What to coverDescribe how you would integrate tools like Arize and Dynatrace to monitor agent performance and reliability. Explain the metrics you would prioritize to detect drift or failures in production.
Technical Formalization of Business Requirements
What to coverDescribe your process for translating ambiguous business needs into structured technical requirements for an AI agent. Provide an example of how you ensure the final solution remains aligned with platform standards.
Containerization and Deployment Strategies
What to coverDiscuss the role of Docker and Kubernetes in deploying agentic workflows. Explain how you manage environment consistency and scaling for AI applications in a highly regulated banking infrastructure.
Integrating External Data and Tools
What to coverExplain how you would implement tools like Fact MCP or STT within an agentic framework. Address the challenges of maintaining data integrity and security when agents interact with external systems.
Continuous Evolution of AI Frameworks
What to coverHow do you incorporate feedback from project teams into the core internal Agentic Framework? Suggest a workflow for gathering field insights and prioritizing new feature development.
LLM Selection and Optimization
What to coverDiscuss the criteria you use to select appropriate LLMs for different agentic tasks. Address considerations such as latency, cost, and accuracy when deploying these models at scale.
Behavioural practice
Evangelizing New Technology to Stakeholders
What to coverDescribe a time you had to communicate a complex technical framework to non-technical stakeholders. How did you ensure they understood the value and adopted the new best practices?
Navigating Ambiguity in AI Projects
What to coverShare an example of a project where you had to solve an unprecedented problem in an uncharted area of AI. How did you maintain focus and drive the project toward a successful outcome?
Collaborative Problem Solving in Multi-disciplinary Teams
What to coverDescribe a situation where you had to work with diverse teams to implement a solution. How did you balance empathy for user needs with the technical constraints of the platform?
Proactive Learning and Adaptability
What to coverGive an example of how you have proactively stayed ahead of the rapidly evolving AI landscape. How have you applied this new knowledge to improve your team's existing processes or frameworks?
02
Sharpen your knowledge
Topics to prepare
Agentic Architecture Patterns
Review the conceptual design of multi-agent systems, focusing on state management, tool-use, and human-in-the-loop workflows. Exercise: Draft a high-level architecture diagram for a hypothetical banking process (e.g., automated document verification) that uses an agentic framework to handle exceptions and escalate to humans, ensuring scalability and robustness.
Technical Formalization of Business Requirements
Practice translating ambiguous business needs into structured technical specifications suitable for AI implementation. Exercise: Take a complex, non-technical business requirement and break it down into a sequence of agent tasks, defining clear inputs, outputs, and decision-making criteria for each step.
Skills to revise
LangGraph Implementation
Gain hands-on experience with stateful, multi-actor applications using LangGraph. Exercise: Build a simple graph-based agent that performs a multi-step task, such as retrieving data from an API, processing it with an LLM, and deciding whether to loop back for more information or finalize the output.
Google AI SDK Integration
Develop proficiency in utilizing the Google AI SDK for model interaction and orchestration. Exercise: Create a script that integrates the SDK to perform a specific task, such as structured data extraction from unstructured text, ensuring proper error handling and response parsing.
AI Observability and Monitoring
Understand how to monitor agentic workflows using tools like Arize or Dynatrace. Exercise: Simulate an agentic workflow and configure basic telemetry to track latency, token usage, and error rates, reflecting the need for production-ready AI systems.
04
Your preparation checklist
Prepare an Agentic Architecture Case Study
Develop a project walkthrough demonstrating your experience with LangGraph or similar orchestration frameworks. Focus on how you designed a scalable, production-ready agentic workflow, specifically highlighting how you handled state management, error recovery, and integration with external tools.
Formalize Your Technical Communication Strategy
Prepare a summary of how you translate complex AI requirements into actionable technical specifications. Be ready to explain a time you evangelized a new technical framework to non-technical stakeholders or project teams to drive adoption.
Review AI Platform Observability and Deployment
Reflect on your experience using tools like Arize and Dynatrace for monitoring AI performance. Prepare to discuss how you ensure robustness in production environments using Docker and Kubernetes, and how you use feedback loops to iterate on framework features.
Draft Strategic Questions for the AI Platform Team
Formulate thoughtful questions regarding the 'Agentic Bootstrap' initiative, such as: 'What are the most common technical hurdles project teams face when adopting the internal framework?' or 'How does the team balance the need for rapid AI innovation with the strict security and compliance requirements of a global bank?'
Synthesize Your Experience with LLM Implementation
Create a concise narrative of your 8+ years of experience that highlights your ability to bridge the gap between theoretical LLM capabilities and practical business implementation, specifically referencing your work with Google AI SDK or similar enterprise-grade tools.
Availability last checked: 18 Oct 2026. Status can change after a check; confirm on the employer’s website. Report an issue · Our checking policy
Share this opportunityKnow someone who would be a great fit?