New opportunity

AI ML Engineer

Delta Global Technology Hub · Bangalore, India

About this role

The AI ML Engineer at Delta Global Technology Hub will work with business and technology stakeholders to translate opportunities into well-defined AI problems. You will develop production-grade AI services, APIs, and microservices using sound software engineering principles. The role involves building solutions using techniques such as generative AI, NLP, retrieval, classification, prediction, recommendation, and optimization. You will develop AI application workflows including prompting, agent orchestration, and RAG, while maintaining data pipelines for ingestion, indexing, and model serving. Responsibilities include defining evaluation approaches, deploying and monitoring AI solutions in cloud environments, and investigating production issues to drive lifecycle improvements. You will integrate AI capabilities with enterprise systems and contribute to technical documentation and CI/CD practices. Minimum qualifications include a Bachelor's degree in a relevant field and 3+ years of professional experience in software engineering, applied ML, data science, or AI engineering, with hands-on Python development. You must have experience with LLMs, AI application patterns, and deploying containerized workloads on cloud platforms like AWS or Azure. Preferred qualifications include a Master's degree, experience with RAG, enterprise search, conversational AI, and knowledge of the airline or travel domain. The role requires strong communication skills and the ability to balance quality, reliability, and cost in production environments.

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

Skills for this role

PythonMachine LearningNatural Language ProcessingGenerative AILarge Language ModelsRetrieval-Augmented GenerationAPI DevelopmentMicroservicesCloud ComputingAWSAzureCI/CDDevOpsObservabilityVector SearchPrompt EngineeringAgent Orchestration

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

Production-Grade AI Development
The role requires moving beyond experimentation to building robust, scalable AI services and microservices. You must demonstrate proficiency in software engineering fundamentals, including modular design, CI/CD, and containerized deployment on cloud platforms like AWS or Azure, ensuring that AI solutions are reliable and maintainable in a production environment.
AI Workflow Orchestration and RAG
A core priority is the design and implementation of complex AI application workflows. This includes building RAG pipelines, managing agent orchestration, and handling prompt engineering. You must be capable of maintaining the full data lifecycle, from ingestion and indexing to model serving and retrieval.
Stakeholder Translation and Evaluation
You must bridge the gap between business opportunities and technical AI solutions. This involves defining clear evaluation metrics—using both automated tests and human review—to ensure that AI outputs meet business outcomes and quality standards, while clearly communicating risks and trade-offs to non-technical stakeholders.

Likely challenges to think through

Balancing Performance and Cost
A significant challenge is the requirement to balance quality, reliability, latency, and cost in production. Prepare by being ready to discuss how you optimize model inference, manage cloud resource consumption, and make architectural decisions that prevent runaway costs while maintaining high service availability.
Managing Probabilistic System Risks
Because the role involves LLMs and generative AI, you will face the inherent unpredictability of these systems. Prepare to discuss your approach to implementing guardrails, content-safety controls, and prompt-injection protections to mitigate operational and security risks in an enterprise environment.
Integration with Legacy Enterprise Systems
Integrating modern AI capabilities into existing airline and travel technology platforms can be complex. Prepare to discuss your experience with asynchronous processing, distributed systems, and API design, specifically focusing on how you ensure seamless interoperability between new AI services and established enterprise infrastructure.

Practice your answers

Technical practice

Designing RAG Pipelines

What to coverExplain the components of a Retrieval-Augmented Generation pipeline, including document ingestion, vector indexing, and retrieval strategies. Discuss how you would handle data privacy and ensure the retrieved context is relevant to the user query.

Productionizing AI Services

What to coverDescribe your approach to deploying containerized AI models in a cloud environment like AWS or Azure. Focus on how you balance latency, scalability, and cost while maintaining high reliability for production services.

Evaluating LLM Applications

What to coverHow do you define and implement evaluation metrics for generative AI workflows? Suggest a mix of automated testing, quality metrics, and human-in-the-loop review processes to ensure model performance.

Observability in AI Systems

What to coverWhat specific logs, traces, and metrics do you monitor to investigate production issues in AI applications? Explain how you use this data to drive lifecycle improvements and identify model drift or performance degradation.

Agent Orchestration and Tool Use

What to coverDiscuss the challenges of building agentic workflows that involve tool use and structured outputs. How do you manage conversational context and ensure the agent remains within defined guardrails?

CI/CD for Machine Learning

What to coverDescribe how you integrate CI/CD practices into an AI development lifecycle. Focus on how you automate testing for both code and model artifacts to ensure consistent deployments.

Handling Prompt Injection and Security

What to coverWhat strategies do you employ to protect AI applications against prompt injection and unauthorized data access? Discuss the importance of content-safety controls when integrating LLMs into enterprise systems.

Software Engineering for AI

What to coverThe role emphasizes sound software engineering principles. Explain how you apply modular design and version control to AI projects to ensure they are maintainable and scalable within a larger enterprise architecture.

Behavioural practice

Translating Business Needs to AI Problems

What to coverDescribe a time you worked with non-technical stakeholders to define an AI project. How did you translate their business opportunity into a technical problem while managing expectations regarding limitations and risks?

Balancing Technical Trade-offs

What to coverGive an example of a project where you had to balance competing priorities like latency, cost, and model quality. How did you communicate these trade-offs to your team or stakeholders to reach a decision?

Collaborating in Diverse Teams

What to coverShare an experience where you had to collaborate with a cross-functional team to deliver an AI solution. How did you ensure diverse perspectives were considered and integrated into the final product?

Taking Ownership of Production Outcomes

What to coverTell me about a time you identified a production issue in an AI system. What steps did you take to investigate the root cause, and how did you ensure the fix improved the long-term reliability of the service?

Sharpen your knowledge

Topics to prepare

Retrieval-Augmented Generation (RAG) Architecture
The role explicitly requires building workflows involving retrieval and indexing. Review the end-to-end RAG pipeline, including document ingestion, vector database selection, semantic search, and context window management. This is critical for the preferred qualification in enterprise search and document management.
Production AI Lifecycle and Observability
The position emphasizes deploying, monitoring, and investigating production issues. Study how to implement logging, tracing, and quality metrics for LLM-based applications. Focus on balancing latency, cost, and reliability, as well as handling model evaluation through automated tests and human review.
AI Application Patterns and Agent Orchestration
Understand common patterns such as structured outputs, tool integration, and agentic workflows. Practice designing systems where models interact with external APIs or enterprise systems, as the role requires integrating AI capabilities into existing technology platforms.

Skills to revise

Python for Backend AI Services
Develop a microservice using a modern Python web framework (e.g., FastAPI or Flask) that exposes an AI model endpoint. Ensure the code follows sound software engineering principles like modular design, unit testing, and version control, which are core requirements for this role.
Cloud-Native Deployment (AWS/Azure)
Practice containerizing an AI application using Docker and deploying it to a cloud environment. Focus on CI/CD integration and managing infrastructure as code, as the role requires hands-on experience with containerized workloads on major cloud platforms.
Prompt Engineering and Guardrails
Refine techniques for prompt design, including handling conversational context and implementing safety controls. Research methods for preventing prompt injection and managing sensitive data, which aligns with the preferred qualifications for content-safety and responsible AI.

Your preparation checklist

Prepare a project walkthrough focusing on RAG and Agentic workflows
Develop a concise presentation of a past project where you implemented RAG or agent orchestration. Highlight how you handled data ingestion, indexing, and the specific LLM patterns used to solve a business problem, ensuring you can explain your architectural choices.
Review cloud-native deployment and observability strategies
Be prepared to discuss how you deploy containerized AI workloads on AWS or Azure. Focus on your experience with CI/CD pipelines, monitoring model performance, and investigating production issues using logs and traces to balance latency and cost.
Draft responses for technical trade-off scenarios
Prepare examples of how you have communicated technical limitations, risks, or uncertainty to non-technical stakeholders. Focus on how you balanced quality, reliability, and cost when selecting AI techniques for production environments.
Research airline and travel industry AI use cases
Familiarize yourself with how AI is applied in the travel domain, such as conversational AI for customer service, recommendation engines, or operational optimization, to demonstrate your ability to align technical solutions with business goals.
Formulate strategic questions for the interviewers
Prepare questions regarding the team's current evaluation frameworks for AI quality, how they manage data privacy and security in their LLM pipelines, and how the engineering team collaborates with business stakeholders to define new AI opportunities.

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 India. Matched to this role, not your profile.

Explore more jobs

Finding similar opportunities…