New opportunity

LLM Full Stack Engineer

Accenture · Ahmedabad, India

About this role

The LLM Full Stack Engineer develops AI-driven applications that integrate large language models with enterprise services. Based at Accenture’s Ahmedabad office, this full-time role spans front-end and server-side development, API design, deployment, and application optimization.

Responsibilities

Design and implement scalable applications that connect LLMs with enterprise systems; develop APIs and refine system architecture as business and technical needs evolve.
Improve application performance, scalability, and reliability, and drive improvements to development workflows and deployment practices.
Act as a subject-matter expert, manage and mentor team members, make team decisions, and contribute to decisions across multiple teams.
Work with stakeholders to gather requirements, translate them into technical specifications, and solve problems within and across teams.

Requirements

Proficiency in Python, with a minimum of 7.5 years of Python experience. The posting also states a minimum of 7.5 years of experience for the role; its job header lists an experience band of 5–10 years.
Experience developing and integrating APIs using modern frameworks and tools; strong understanding of server-side technologies and front-end development principles.
Familiarity with DevOps practices, including continuous integration, continuous deployment, and automation; ability to optimize AI applications; and knowledge of cloud platforms and containerization for deployment.
15 years of full-time education. No additional good-to-have skills are specified.

For full details about this role, click “Apply on company site” to view the employer’s original posting.

Skills for this role

PythonLarge Language ModelsAPI developmentFront-end developmentServer-side developmentDevOpsContinuous integrationContinuous deploymentAutomationCloud platformsContainerizationAI application optimizationTechnical leadershipStakeholder managementMentoring

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

Lead LLM application architecture
The role leads the design and implementation of scalable applications integrating LLMs with enterprise services, while refining architecture as needs evolve. Prepare to explain architecture decisions and their trade-offs.
Deliver across the full stack
The posting calls for Python, API development and integration, server-side technologies, and front-end development principles. Prepare an example showing how these parts work together in an application.
Improve performance and deployment
The role calls for optimizing AI applications for performance, scalability, and reliability, and improving workflows through CI/CD and automation. Cloud platforms and containerization support deployment.
Make decisions across teams
The engineer is expected to act as an SME, manage and mentor team members, contribute to decisions across teams, and turn stakeholder requirements into technical specifications. Prepare examples of decisions and how they were communicated.

Likely challenges to think through

Balancing full-stack scope with AI optimization
Preparation hypothesis: Work spanning the front end, APIs, enterprise integration, and LLMs may make it difficult to locate a performance or reliability issue. Prepare an example of narrowing down a bottleneck and choosing what to improve first.
Evolving architecture without disrupting delivery
Preparation hypothesis: Refining architecture as business and technical needs change may conflict with keeping applications and deployments stable. Prepare to discuss an incremental change and the trade-off between immediate delivery and longer-term scalability.
Aligning decisions across stakeholders and teams
Preparation hypothesis: Translating requirements into specifications while contributing to decisions across teams may involve competing priorities. Prepare an example of clarifying requirements, explaining options, and reaching a technical decision.

Practice your answers

Technical practice

How would you structure a Python service that connects an LLM to an enterprise application?

What to coverThe posting requires Python and describes integrating LLMs with enterprise services. Preparation suggestion: explain how you would separate application logic, model integration, and service interfaces so each can be tested and changed independently.

How would you design an application flow between an LLM and an enterprise system?

What to coverIntegrating LLMs with enterprise systems is central to the role. Preparation suggestion: walk through request and response flow, including how you would handle unavailable services and evaluate whether the integration meets its intended purpose.

What would you consider when designing an API for an AI-driven application?

What to coverThe posting calls for developing and integrating robust APIs. Preparation suggestion: discuss interface clarity, validation, error handling, and how you would evolve an API without disrupting its consumers.

How would you divide work between the front end and server side of an LLM application?

What to coverThe role spans front-end and server-side development. Preparation suggestion: explain where you would place interaction logic versus service integration, and how that division affects usability and maintainability.

How would you investigate slow performance in an AI application?

What to coverOptimizing AI application performance is an explicit responsibility. Preparation suggestion: describe how you would measure the request path, isolate the bottleneck, and weigh latency improvements against other application needs.

How would you make an LLM-integrated application scale as usage grows?

What to coverThe posting calls for scalable AI-driven applications. Preparation suggestion: identify potential pressure points across application services and integrations, then explain how you would test whether a proposed change improves capacity.

How would you improve the reliability of an application that depends on external services?

What to coverThe role explicitly includes optimizing AI applications for reliability. Preparation suggestion: discuss detecting failures, handling interrupted requests, and choosing responses that preserve a usable application experience.

How would you use CI, deployment practices, and automation for this application?

What to coverThe posting names continuous integration, continuous deployment, and automation. Preparation suggestion: outline checks and deployment steps you would automate, and explain how you would reduce the risk of releasing a broken integration.

What would you evaluate when deploying the application using containers and a cloud platform?

What to coverKnowledge of cloud platforms and containerization for deployment is listed. Preparation suggestion: discuss configuration, service connectivity, and operational visibility without assuming the employer uses a particular platform or tool.

When would you change the architecture of an existing LLM application?

What to coverThe posting describes refining architecture as business needs and technology evolve. Preparation suggestion: explain how you would identify a design constraint, compare incremental changes with a larger redesign, and justify the decision.

Behavioural practice

Tell me about a time you turned stakeholder needs into technical specifications.

What to coverGathering requirements and translating them into specifications is a stated responsibility. Preparation suggestion: use a real situation, your actions to resolve ambiguity and document decisions, and the resulting outcome.

Describe a consequential technical decision you made with a team.

What to coverThe role includes subject-matter expertise and responsibility for team decisions. Preparation suggestion: describe the situation, how you weighed options and involved others, and the result of the decision.

Tell me about a time you mentored a junior team member.

What to coverMentoring junior colleagues and sharing knowledge are explicit duties. Preparation suggestion: give a real situation, the support you provided, and an observable result without overstating your contribution.

Describe a problem you solved across multiple teams.

What to coverThe posting calls for cross-team collaboration and solutions beyond the immediate team. Preparation suggestion: explain the situation, how you aligned the teams on actions, and what changed as a result.

Tell me about a development workflow or application improvement you led.

What to coverDriving continuous improvement in workflows and application performance is part of the role. Preparation suggestion: describe the initial problem, the change you made, and evidence of its result, including any trade-offs.

Sharpen your knowledge

Topics to prepare

LLM and enterprise-system architecture
Suggested revision exercise: sketch how an application would connect an LLM to an enterprise service, then explain where errors, latency, and changing business needs affect the design. The posting explicitly calls for these integrations and evolving system architecture.
Full-stack API design
Suggested revision exercise: diagram the flow from a front-end interaction through an API and server-side logic, and explain how you would keep the interface and API contract aligned. The role spans front-end principles, server-side technologies, and API development.
Performance, scalability, and reliability
Suggested revision exercise: take a hypothetical slow AI request and explain how you would distinguish LLM latency from API or enterprise-service bottlenecks, then prioritize improvements. The posting calls for optimizing AI applications on all three dimensions.
Deployment and delivery practices
Suggested revision exercise: outline how continuous integration, continuous deployment, automation, cloud platforms, and containerization fit into an application release. These are explicitly named in the posting; no particular platform or tool is specified.
Technical leadership and requirements
Suggested revision exercise: turn a hypothetical stakeholder request into technical specifications, then explain a design decision and how you would communicate it to another team and a junior engineer. The role includes stakeholder coordination, team decisions, cross-team problem-solving, and mentoring.

Skills to revise

Python implementation
Suggested revision exercise: write a small Python server-side component with clear input handling, error handling, and tests. Python is the posting’s must-have skill, and it specifies at least 7.5 years of Python experience.
API development and integration
Suggested revision exercise: implement an API endpoint that calls a mock enterprise service; test successful responses, invalid inputs, and upstream failures. Developing and integrating APIs is explicitly required; the mock service is only a practice device.
LLM application integration
Suggested revision exercise: build a small Python flow that sends a request to an LLM interface and returns its result through an API, accounting for timeouts and failures. This practices the advertised LLM-integration work without assuming a particular provider.
Front-end and server-side connection
Suggested revision exercise: create a minimal front-end interaction that submits input to your API and displays success and error states. The role calls for balancing front-end and back-end work, but specifies no front-end framework.
Delivery and optimization walkthrough
Suggested revision exercise: prepare an automated build-and-test workflow for the practice application, outline a containerized deployment, and measure one request bottleneck before proposing a fix. This combines the posting’s DevOps, deployment, and application-optimization expectations without presuming a specific tool.

Your preparation checklist

Prepare a Python evidence sheet
The posting requires Python proficiency and at least 7.5 years of Python experience. Prepare a dated summary of Python work, your contributions, and outcomes; have your education history ready for the stated 15-year full-time education requirement.
Build an LLM application walkthrough
Choose a relevant project, if you have one, and prepare a short walkthrough of how the application connected an LLM with other services. Show your own front-end and server-side contributions without implying that the employer uses the same design.
Practice an enterprise integration design
Sketch a hypothetical scalable application connecting an LLM to an enterprise system. Explain the API boundaries, Python server-side components, front-end interactions, and how you would adapt the architecture as requirements change.
Document an optimization example
Prepare before-and-after evidence from work on application performance, scalability, or reliability, where available. Explain the measurement, trade-offs, and what you would investigate next.
Outline a deployment approach
The role calls for CI/CD, automation, cloud-platform knowledge, and containerization. Prepare a deployment diagram and be ready to explain how you would test, release, monitor, and recover an AI application; treat the diagram as your proposed approach, not Accenture’s process.
Select leadership and stakeholder examples
Prepare concise accounts of a team decision, mentoring contribution, and stakeholder requirement translated into a technical specification. Clarify your responsibility and the outcome in each example.
Draft questions for the employer
Ask which enterprise integrations and front-end responsibilities are in scope, how success is measured for AI application performance and reliability, and how decisions are shared across the teams mentioned in the posting.

Availability last checked: 5 Nov 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…