New opportunity

Senior Technical Specialist - AI and Enterprise Applications

London Stock Exchange Group (LSEG) · Taguig City, Philippines

About this role

The Senior Technical Specialist - AI and Enterprise Applications will provide expert-level support for both AI-enabled and non-AI enterprise applications at LSEG. This role serves as a senior escalation point for complex technical issues, requiring deep analytical skills and a strong understanding of AI product architectures. Key responsibilities include investigating and resolving incidents related to AI response quality, prompt execution, model output, and system integrations. You will collaborate with product, engineering, and support teams to drive resolution and improve the overall customer experience. Responsibilities: Act as a senior escalation point for complex application issues. Troubleshoot AI-specific issues including prompt failures, model inconsistencies, and retrieval/context errors. Diagnose issues across authentication (SSO, OAuth, OIDC), data connectivity, and API integrations. Support the adoption of AI technologies by assisting stakeholders with prompt engineering, grounding mechanisms, and responsible AI practices. Develop knowledge articles, troubleshooting guides, and FAQs to enable users and support teams. Provide actionable feedback to product and engineering teams based on customer interactions. Requirements: Experience in a customer-facing technical support or service management role, ideally within SaaS, data, or financial technology. Solid understanding of AI concepts including LLMs, generative AI, AI agents, prompt engineering, and tool-calling frameworks. Strong analytical and troubleshooting skills with the ability to interpret logs, telemetry, and system diagnostics. Proficiency with case management platforms like Salesforce Service Cloud or ServiceNow. Excellent communication skills to convey technical concepts to diverse audiences. Ability to work cross-functionally with access management, licensing, and entitlement teams.

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 AIAI AgentsPrompt EngineeringModel Context Protocol (MCP)Technical SupportIncident ManagementRoot Cause AnalysisSSOOAuthOIDCSalesforce Service CloudServiceNowAPI IntegrationData Connectivity

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

Complex Incident Resolution and Escalation
Serving as the senior escalation point for AI-enabled and enterprise application issues that bypass standard support channels. This requires deep analytical skills to perform root cause analysis across authentication, data connectivity, and API integration layers to meet established SLAs.
AI Solution Troubleshooting and Optimization
Diagnosing AI-specific failures such as prompt execution errors, model output inconsistencies, and retrieval/grounding issues. You must understand tool-calling frameworks and Model Context Protocol (MCP) to ensure AI services integrate correctly with enterprise data sources.
Stakeholder Enablement and Knowledge Management
Developing technical documentation, FAQs, and troubleshooting guides to empower users and support teams. You will act as a trusted advisor, assisting stakeholders with prompt engineering and responsible AI practices to drive successful technology adoption.
Cross-Functional Feedback Loop
Acting as the voice of the customer by providing actionable feedback to product and engineering teams based on incident trends and user interactions. This involves partnering with access management and entitlement teams to resolve complex permission-related issues.

Likely challenges to think through

Distinguishing AI Behavior from System Failure
A significant challenge is isolating whether an issue is a hallucination or model limitation versus a technical failure in the underlying integration, authentication, or data pipeline. Prepare by practicing how to systematically interpret logs and telemetry to pinpoint the exact layer of failure.
Balancing Technical Depth with Non-Technical Communication
You must explain complex AI concepts like grounding or tool-calling to diverse audiences while maintaining high-level technical rigor. Prepare by refining your ability to translate technical diagnostic findings into clear, actionable insights for both engineering teams and business stakeholders.
Navigating Enterprise Security and Governance
Supporting AI adoption within a highly regulated financial environment requires strict adherence to privacy and security protocols. Prepare by reviewing how to troubleshoot access and entitlement issues (SSO, OAuth, OIDC) without compromising system security or compliance standards.

Practice your answers

Technical practice

Troubleshooting AI Model Inconsistencies

What to coverExplain your methodology for diagnosing non-deterministic model outputs. Focus on how you differentiate between prompt-related issues, context window limitations, and underlying model behavior.

Authentication and Identity Management

What to coverDescribe how you would troubleshoot a user access issue involving SSO, OAuth, or OIDC. Discuss the logs or diagnostic tools you would prioritize to isolate whether the failure occurs at the identity provider or the application integration layer.

Tool-Calling and MCP Frameworks

What to coverExplain your understanding of the Model Context Protocol (MCP) and how you would troubleshoot a failure where an AI agent fails to correctly invoke an external tool or API. Suggest how you would validate the integration between the agent and the data source.

Root Cause Analysis for Enterprise Integrations

What to coverDescribe a systematic approach to performing root cause analysis when an AI-enabled application fails to retrieve data from an enterprise database. Include how you verify connectivity, permissions, and API response integrity.

Prompt Engineering and Grounding

What to coverHow do you assist stakeholders in improving AI response quality through prompt engineering and grounding mechanisms? Discuss the trade-offs between system-level prompt adjustments and data-source retrieval improvements.

Interpreting System Diagnostics

What to coverWhen faced with a complex incident, how do you correlate telemetry and logs across multiple layers, such as cloud services and application platforms? Provide an example of how you would isolate a bottleneck in an integrated system.

Responsible AI and Governance

What to coverHow do you incorporate privacy, security, and governance considerations when supporting the adoption of AI technologies? Address how you balance user enablement with the need for strict adherence to organizational AI policies.

Case Management and Documentation

What to coverExplain your process for maintaining high-quality documentation in platforms like Salesforce or ServiceNow. Discuss how you ensure that technical knowledge articles remain actionable for both support teams and end-users.

Behavioural practice

Managing Complex Escalations

What to coverDescribe a situation where you acted as a senior escalation point for a critical technical issue. How did you manage stakeholder expectations while coordinating the resolution across multiple cross-functional teams?

Communicating Technical Concepts

What to coverProvide an example of when you had to explain a complex technical failure to a non-technical stakeholder. How did you tailor your communication to ensure they understood the impact and the path to resolution?

Cross-Functional Collaboration

What to coverDescribe a time you worked with engineering or product teams to drive a permanent fix for a recurring issue. What was your role in providing actionable feedback and ensuring the customer's voice was represented?

Continuous Improvement and Mentorship

What to coverGive an example of how you identified a gap in support processes or tools and took the initiative to improve them. How did you share these best practices or mentor colleagues to elevate the team's overall performance?

Sharpen your knowledge

Topics to prepare

AI Retrieval and Grounding Mechanisms
Review how RAG (Retrieval-Augmented Generation) architectures function, specifically focusing on how models access external knowledge bases to reduce hallucinations. Exercise: Diagram the data flow from a user query to a vector database and back to the LLM, identifying potential failure points in retrieval or context injection.
Authentication and Authorization Protocols
Deepen understanding of SSO, OAuth, and OIDC workflows within enterprise environments. Exercise: Map out the handshake process for an OIDC flow and identify common error scenarios, such as token expiration or scope misconfiguration, that would trigger a support escalation.
Tool-Calling and Model Context Protocol (MCP)
Study how AI agents use tool-calling frameworks to interact with external APIs and enterprise systems. Exercise: Research the Model Context Protocol (MCP) to understand how it standardizes connections between AI models and data sources, and simulate troubleshooting a failed tool execution.

Skills to revise

Root Cause Analysis (RCA) for AI Systems
Practice isolating whether an issue is caused by the model, the prompt, the integration layer, or the underlying data source. Exercise: Take a hypothetical incident report of 'incorrect AI output' and create a decision tree to determine if the root cause is a prompt failure, a data connectivity issue, or a model hallucination.
Technical Log and Telemetry Interpretation
Develop proficiency in reading system logs to diagnose complex integration failures. Exercise: Review sample application logs containing API error codes (e.g., 401, 403, 500) and trace them back to potential authentication or connectivity issues within a cloud-based enterprise architecture.
Prompt Engineering for Support
Refine the ability to debug and optimize prompts for enterprise use cases. Exercise: Take a vague user prompt that produces inconsistent results and iterate on it using techniques like few-shot prompting or chain-of-thought to improve output reliability and grounding.

Your preparation checklist

Prepare a technical case study on AI troubleshooting
Draft a structured walkthrough of a complex incident you resolved involving AI or enterprise software. Focus on your methodology for isolating root causes across layers like authentication (SSO/OAuth), API integrations, or model output inconsistencies, demonstrating your analytical approach to telemetry and logs.
Develop a framework for explaining AI concepts to non-technical stakeholders
Prepare a concise explanation of how LLMs, retrieval-augmented generation (RAG), or tool-calling frameworks function. Practice translating these concepts into business-relevant terms to demonstrate your ability to act as a trusted advisor for internal and external users.
Create a sample knowledge management artifact
Draft a template for a troubleshooting guide or FAQ article designed for a complex technical issue. This should demonstrate your ability to document technical workflows, provide actionable steps for support teams, and maintain clarity for diverse audiences.
Formulate questions regarding LSEG's AI support ecosystem
Prepare thoughtful questions about how the team manages AI-specific escalations, such as: 'How does the team balance rapid incident resolution with the need for rigorous root cause analysis in AI-enabled products?' or 'What are the primary challenges in maintaining grounding mechanisms for your current enterprise AI integrations?'
Review your experience with enterprise service management tools
Be prepared to discuss your proficiency with platforms like Salesforce Service Cloud or ServiceNow. Specifically, highlight how you have used these tools to track operational metrics, manage SLAs, and provide feedback to engineering teams based on recurring issue trends.

Availability has not yet been verified. 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 Philippines. Matched to this role, not your profile.

Explore more jobs

Finding similar opportunities…