New opportunity

Agentic Solutions Engineer

BNP Paribas India Solutions · Mumbai, India

About this role

As an Agentic Solutions Engineer within the AI Platform team at BNP Paribas, you will act as a bridge between cutting-edge AI capabilities and business implementation. You will lead the 'Agentic Bootstrap' initiative, empowering project teams to structure requirements, define technical solutions, and adopt agentic frameworks to accelerate the transition from conceptual AI ideas to production-ready workflows. Responsibilities include framework evangelism, providing hands-on technical guidance to project teams, and contributing to the evolution of internal frameworks based on field feedback. Candidates must possess an Engineering or equivalent degree with at least 8 years of relevant experience. Required technical skills include expertise in LLMs, Generative AI frameworks, agentic orchestration (e.g., LangGraph), Google AI SDK, and robust application architecture. Proficiency with tools such as Docker, Kubernetes, Arize, and Dynatrace is expected. Strong behavioral competencies, including analytical synthesis, communication, adaptability, and a collaborative mindset, are essential for success in this global, 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 SDKApplication DesignArchitectureTechnical FormalizationFact MCPSTTArizeDynatraceDockerKubernetesAnalytical ThinkingCommunicationAdaptability

Checking your profile…

Preparation suggestions, not the employer’s actual interview questions. Always check the original posting for current requirements.

Understand the role

What matters most

Leading the Agentic Bootstrap Initiative
The primary mission is to drive the adoption of agentic frameworks across project teams. You must be able to translate high-level business requirements into structured technical solutions, ensuring that conceptual AI ideas are successfully transitioned into production-ready, scalable workflows.
Framework Evangelism and Technical Guidance
You are expected to act as a bridge between the AI Platform team and various business units. This involves communicating the roadmap and best practices of internal frameworks while providing hands-on technical support to ensure project teams align with established platform standards.
Continuous Framework Evolution
Beyond implementation, you must actively gather feedback from the field to improve internal frameworks. This requires a proactive approach to identifying optimizations and new features that enhance the overall utility and performance of the bank's agentic infrastructure.

Likely challenges to think through

Navigating Complex Stakeholder Environments
As a bridge between technical AI teams and diverse business units, you may face resistance to new workflows or difficulty in aligning non-technical stakeholders with complex architectural requirements. Prepare by demonstrating your ability to synthesize technical concepts into clear, actionable business language.
Balancing Standardization with Project Flexibility
The role requires enforcing platform standards while supporting diverse project needs. The challenge lies in maintaining a robust, scalable architecture without stifling the innovation required for unique use cases. Prepare by discussing how you manage trade-offs between rigid framework compliance and the need for custom implementation.
Rapidly Evolving AI Landscape
The field of agentic orchestration is moving quickly. You must stay ahead of the curve while ensuring that the solutions you implement remain stable and production-ready. Prepare by highlighting your process for continuous learning and how you evaluate the maturity of new tools before integrating them into a banking environment.

Practice your answers

Technical practice

Agentic Orchestration with LangGraph

What to coverExplain how you would design a multi-agent workflow using LangGraph to handle complex, stateful tasks. Discuss the trade-offs between cyclic and acyclic graph structures in the context of ensuring reliability in production-ready AI applications.

Scalable AI Architecture Design

What to coverDescribe your approach to architecting a scalable AI platform that integrates LLMs into existing enterprise workflows. Focus on how you ensure robustness, latency management, and modularity when deploying these systems within a large-scale banking environment.

LLM Deployment and Monitoring

What to coverHow do you approach the observability of production AI agents using tools like Arize and Dynatrace? Detail your strategy for detecting model drift, hallucination, or performance degradation in real-time.

Containerization and Orchestration in AI

What to coverDiscuss the role of Docker and Kubernetes in deploying generative AI frameworks. Explain how you manage resource allocation and scaling for compute-intensive LLM inference workloads.

Technical Formalization of Business Requirements

What to coverProvide an example of how you translate ambiguous business requirements into a structured technical specification for an AI agent. Focus on your process for defining scope, constraints, and success metrics.

Google AI SDK Integration

What to coverDiscuss your experience integrating the Google AI SDK into enterprise applications. Highlight how you handle authentication, rate limiting, and cost management when scaling these integrations across multiple project teams.

Framework Evolution and Feedback Loops

What to coverAs an engineer leading a bootstrap initiative, how do you gather and prioritize feedback from project teams to evolve internal AI frameworks? Explain how you balance immediate project needs with long-term platform roadmap goals.

Handling Unstructured Data in AI Workflows

What to coverDescribe your strategy for incorporating Speech-to-Text (STT) or other unstructured data inputs into agentic workflows. Address the challenges of data quality and pre-processing in a banking context.

Behavioural practice

Framework Evangelism and Stakeholder Management

What to coverDescribe a situation where you had to convince a skeptical team to adopt a new technical framework. How did you communicate the benefits, address their concerns, and ensure successful implementation?

Navigating Ambiguity in AI Projects

What to coverShare an example of a project where you had to solve an unprecedented technical problem with limited guidance. How did you approach the research, experimentation, and final decision-making process?

Collaborative Problem Solving in Multi-disciplinary Teams

What to coverTell us about a time you worked with a diverse, global team to deliver a complex solution. How did you ensure alignment, manage communication barriers, and leverage different perspectives to achieve the result?

Adaptability to Rapid Technological Change

What to coverThe AI field evolves very quickly. Provide an example of how you have proactively updated your skills or changed your technical approach in response to a major industry shift.

Empathy in Technical Leadership

What to coverDescribe a time when you had to support a team member or project group struggling with a transition to new technology. How did you balance technical guidance with the need for empathy and patience?

Sharpen your knowledge

Topics to prepare

Agentic Workflow Architecture
Review the conceptual design of autonomous agent systems, focusing on state management, tool-use, and multi-agent orchestration. Exercise: Draft a high-level architectural diagram for a banking process (e.g., document verification) that transitions from a manual workflow to an agentic one using LangGraph concepts. This is relevant to the 'Agentic Bootstrap' initiative and the requirement to design scalable AI solutions.
Technical Formalization of Business Requirements
Study methods for translating ambiguous business needs into structured technical specifications. Exercise: Take a complex, non-technical business problem and break it down into a sequence of LLM-driven tasks, defining the necessary inputs, outputs, and constraints for each step. This directly supports the 'Technical Formalization' competency required to bridge the gap between business and engineering.

Skills to revise

Agentic Orchestration with LangGraph
Gain hands-on experience building stateful, multi-actor applications using LangGraph. Exercise: Implement a simple cyclical workflow where an agent evaluates its own output and decides whether to refine it or proceed to the next step. This is a core technical requirement for the role's focus on agentic frameworks.
AI Observability and Monitoring
Practice using tools like Arize and Dynatrace to monitor LLM performance, latency, and drift. Exercise: Set up a mock dashboard to track the success rate and latency of a prompt-based application, simulating how you would provide feedback to project teams on production-readiness. This is essential for the 'Continuous Evolution' and 'Solution Guidance' responsibilities.
Containerization and Orchestration
Ensure proficiency in deploying AI services using Docker and Kubernetes. Exercise: Create a Dockerfile for a Python-based LLM service and write a basic Kubernetes deployment manifest to manage its scaling. This is a stated technical requirement for building robust, production-ready AI workflows.

Your preparation checklist

Architect an Agentic Workflow Prototype
Develop a small-scale project using LangGraph and the Google AI SDK to demonstrate your ability to build autonomous, scalable agentic workflows. Prepare to explain your architectural choices regarding state management, tool integration, and error handling in a production-ready context.
Prepare a Technical Formalization Case Study
Select a complex business requirement from your past experience and document how you translated it into a structured technical solution. Focus on your process for defining scope, selecting appropriate AI frameworks, and ensuring the solution aligns with enterprise-grade standards like Docker and Kubernetes.
Review Monitoring and Observability Strategies
Familiarize yourself with how Arize and Dynatrace are used to monitor AI performance and application health. Be ready to discuss how you would implement these tools to track agentic behavior, latency, and drift in a live banking environment.
Formulate Questions on the 'Agentic Bootstrap' Initiative
Prepare thoughtful questions about the current maturity of the internal framework, the primary technical hurdles project teams face during adoption, and how you will balance evangelism with hands-on engineering support.
Refine Your Communication of Technical Synthesis
Practice explaining complex AI concepts to non-technical stakeholders. Prepare examples of how you have successfully guided cross-functional teams through technical transitions, emphasizing your empathy and collaborative approach to change management.

Availability last checked: 18 Oct 2026. Status can change after a check; confirm on the employer’s website. Report an issue · Our checking policy

KEEP EXPLORING

Similar AI jobs

Related skills and specializations in India. Matched to this role, not your profile.

Explore more jobs

Finding similar opportunities…