New opportunity

Gen AI Engineer

Qloron · Hyderabad, India

About this role

The Gen AI Engineer designs, develops, deploys and maintains AI-powered applications using Python, Azure AI services, large language models (LLMs) and retrieval-augmented generation (RAG). The position calls for 6–8 years of overall IT experience and is listed as full-time, with onsite or hybrid arrangements in Mumbai, Pune, Kochi, Chennai, Coimbatore or Hyderabad.

Responsibilities

Build generative AI applications with Azure AI Services and OpenAI models, including RAG solutions that use vector databases and semantic search.
Develop scalable Python backend services and APIs; integrate models such as GPT, Llama and Claude into enterprise applications.
Implement prompt engineering, fine-tuning and model evaluation strategies. Develop AI agents, chatbots and intelligent automation solutions.
Work with cross-functional teams to translate business requirements into AI solutions. Monitor and optimize production applications while following security, governance and compliance standards.

Required skills:

Strong Python programming and hands-on Azure cloud experience, including Azure OpenAI Service and Azure AI Studio.
Understanding of LLMs; experience building RAG pipelines; knowledge of vector databases such as FAISS, Pinecone, ChromaDB or Weaviate and frameworks such as LangChain, LlamaIndex or Semantic Kernel.
Knowledge of prompt engineering, REST API development, microservices architecture, and AI model evaluation and monitoring.

Preferred skills:

Experience with AI agents and multi-agent frameworks; exposure to MLOps and CI/CD; experience with Docker and Kubernetes; knowledge of data engineering and ETL pipelines; and familiarity with Git, Azure DevOps and Agile methodologies.

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

Skills for this role

PythonAzure Cloud ServicesAzure AI ServicesAzure OpenAI ServiceAzure AI StudioAzure Cognitive SearchAzure Machine LearningLarge Language ModelsRetrieval-Augmented GenerationSemantic SearchVector DatabasesFAISSPineconeChromaDBWeaviateLangChainLlamaIndexSemantic KernelPrompt EngineeringFine-TuningModel EvaluationREST APIsMicroservicesAI AgentsMulti-Agent FrameworksMLOpsCI/CDDockerKubernetesETL Pipelines established after work here? no. mark?

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

Build Azure-based GenAI applications
The role calls for designing and deploying applications with Azure AI Services and OpenAI models, using Azure OpenAI, Azure AI Studio, Azure Cognitive Search, and Azure Machine Learning.
Deliver effective RAG solutions
Building and optimizing RAG pipelines with vector databases and semantic search is a stated responsibility. Be ready to explain retrieval design choices and how you assess answer quality.
Engineer enterprise integrations
The role includes scalable Python backend services and REST APIs that integrate LLMs such as GPT, Llama, or Claude into enterprise applications.
Evaluate and improve model behavior
Prompt engineering, fine-tuning, and model evaluation are explicit duties. Prepare to distinguish when each approach is useful and how its results can be measured.
Operate AI applications responsibly
The engineer is expected to collaborate on business requirements, monitor and maintain production applications, and follow security, governance, and compliance standards.

Likely challenges to think through

Balancing RAG quality and responsiveness
Likely preparation hypothesis, not a reported Qloron problem: richer retrieval may improve grounding while adding latency and complexity. Prepare an example of how you would compare retrieval quality, response quality, and performance.
Choosing among improvement methods
Likely preparation hypothesis: a weak answer could call for better retrieval, a prompt change, or fine-tuning. Prepare to explain how evaluation would help identify the cause before selecting an intervention.
Moving from prototype to governed production service
Likely preparation hypothesis: rapid AI iteration can conflict with reliable APIs, monitoring, and security controls. Prepare to describe how you would translate a business need into a deployable service while checking those operational requirements.

Practice your answers

Technical practice

How would you design a RAG application using Azure AI services?

What to coverSuggested preparation: Walk through document ingestion, indexing, semantic retrieval, prompt construction, and generation with Azure OpenAI. Explain how you would keep retrieved content relevant and assess whether the answer is grounded in it.

How would you troubleshoot poor retrieval in a RAG pipeline?

What to coverSuggested preparation: Discuss checks for source-data quality, chunking, indexing, and search results before changing the model. Explain how you would compare retrieval approaches using representative queries and relevance measures.

How would you use Azure AI Studio, Azure OpenAI, and Azure Cognitive Search together?

What to coverSuggested preparation: Describe each service’s role in developing, testing, and serving an application, without assuming a particular deployment design. Address how you would evaluate integration choices against application requirements.

How would you build a scalable Python API for an LLM-powered application?

What to coverSuggested preparation: Cover request validation, timeouts, retries, concurrency, and handling model-service failures. Explain how you would balance responsiveness, reliability, and maintainability in a REST API or microservice.

How would you choose and integrate an LLM for an enterprise application?

What to coverSuggested preparation: Compare relevant factors such as task quality, latency, cost, and integration constraints for models such as GPT, Llama, or Claude. Describe how you would test a choice against the application’s requirements rather than assuming one model always fits.

When would you use prompt engineering, RAG, or fine-tuning?

What to coverSuggested preparation: Explain the different problems each approach can address and the effort needed to maintain it. Discuss how you would establish a baseline and evaluate a change before adopting a more involved approach.

How would you evaluate a generative AI application before release?

What to coverSuggested preparation: Define representative test cases and measures for answer quality, grounding, and failure behavior. Explain how you would compare versions and review errors that aggregate scores might conceal.

How would you design and constrain an AI agent or chatbot?

What to coverSuggested preparation: Describe how an agent would choose actions, use available tools, and handle uncertain or failed steps. Discuss when a simpler chatbot workflow might be preferable to a more autonomous or multi-agent design.

How would you monitor and improve an AI application in production?

What to coverSuggested preparation: Cover service health, latency, failures, and changes in response quality, then explain how findings would guide fixes. As an extension based on the posting’s preferred skills, discuss how CI/CD or containerization could support controlled updates.

How would you address security, governance, and compliance in an LLM application?

What to coverSuggested preparation: Discuss access to source content, treatment of sensitive inputs, and controls around model outputs. Explain how you would check that an implementation follows applicable organizational standards without assuming a specific policy.

Behavioural practice

Tell me about a time you translated a business need into a technical solution.

What to coverSuggested preparation: Use a real situation, the questions you asked to clarify requirements, and the actions you took to define a workable approach. State the result and how you checked whether it met the need.

Describe a time you worked across teams on a technically complex delivery.

What to coverSuggested preparation: Set out the situation, your specific actions to coordinate decisions or resolve a disagreement, and the result. Keep your own contribution distinct from the team’s work.

Tell me about a production issue you investigated and resolved.

What to coverSuggested preparation: Explain the situation, how you narrowed down the cause, and the actions you took to restore or improve the service. Include the result and any follow-up monitoring or prevention work.

Describe a time security or governance constraints changed your technical approach.

What to coverSuggested preparation: Use a real situation to explain the constraint, the trade-off you considered, and the action you took with relevant stakeholders. Describe the result without claiming that a particular control applies at Qloron.

Sharpen your knowledge

Topics to prepare

RAG and semantic retrieval
Suggested exercise: Diagram how documents are indexed, retrieved through vector search, and supplied to an LLM; explain where irrelevant retrieval can degrade an answer. Relevant because the role builds and optimizes RAG solutions using vector databases and semantic search.
LLM adaptation choices
Suggested exercise: Compare prompt engineering and fine-tuning for one enterprise use case, including how you would evaluate the result. Both approaches and model evaluation appear in the responsibilities.
Azure AI service roles
Suggested exercise: Map Azure OpenAI, Azure AI Studio, Azure Cognitive Search, and Azure Machine Learning to their possible roles in an application design. The posting explicitly names all four; the proposed design is preparation, not a prescribed architecture.
Backend and production architecture
Suggested exercise: Sketch a Python API and microservices design for an LLM application, then identify scalability, monitoring, and maintenance concerns. These reflect the stated backend and production responsibilities.
AI security and governance
Suggested exercise: Review a hypothetical enterprise chatbot design for sensitive-data exposure and access-control risks. The posting requires security, governance, and compliance in AI implementations; it does not specify a particular standard.
Agent design
Suggested exercise: Explain when a chatbot might benefit from an agent and how you would assess its actions. Developing agents is a responsibility; multi-agent framework experience is preferred.

Skills to revise

Build a Python REST endpoint
Suggested exercise: Implement a small Python endpoint that accepts a question, calls an LLM, and returns a structured response; explain how you would handle failures. The role calls for scalable Python backend services and REST API development.
Implement a small RAG pipeline
Suggested exercise: Index a small document set in one named vector database, retrieve passages for test questions, and pass them to a model. FAISS, Pinecone, ChromaDB, and Weaviate are examples in the posting, not a requirement to use all four.
Integrate Azure AI services
Suggested exercise: Walk through or prototype a model call using Azure OpenAI Service and inspect the setup in Azure AI Studio. Hands-on experience with both is explicitly required.
Evaluate and refine outputs
Suggested exercise: Create a small question set, record answer quality and retrieval failures, revise prompts, and compare results. This practices the posting’s prompt engineering, model evaluation, and RAG optimization work.
Plan production monitoring
Suggested exercise: Add or outline application logging, failure tracking, and a review step for sensitive inputs in the Python service. This is a suggested implementation exercise for the stated monitoring, maintenance, and security responsibilities.
Prototype a bounded agent
Suggested exercise: Build a simple agent or chatbot for one defined task and test how it behaves when it cannot complete that task. Agent development is listed among responsibilities; multi-agent frameworks are preferred, not required.

Your preparation checklist

Prepare an end-to-end GenAI project walkthrough
The posting calls for designing and deploying AI applications with Python and Azure AI services. Prepare a concise walkthrough covering the use case, your technical decisions, your contribution, deployment, and what changed after release.
Sketch a RAG architecture
The role explicitly includes RAG, vector databases, and semantic search. Draw an ingestion-to-answer flow and be ready to explain retrieval choices, how you would assess answer quality, and which components you have used versus would propose.
Show a Python API design
The posting requires scalable Python backends, REST APIs, and microservices. Prepare an API sketch for an LLM-backed application, including request handling, failure cases, and how it connects to Azure OpenAI or another model.
Bring evidence of model evaluation
The role includes prompt engineering, fine-tuning, evaluation, and monitoring. Prepare an example of how you compared prompts or model outputs, what measures you used, and when you would consider fine-tuning rather than a prompt or retrieval change.
Plan for production and governance questions
The posting calls for maintaining and optimizing production applications while following security, governance, and compliance standards. Outline the monitoring signals, operational risks, and safeguards you would discuss for an enterprise AI application.
Prepare an agent example if relevant
AI agents are a responsibility, while multi-agent frameworks are preferred. If you have relevant work, prepare a brief example showing the agent’s task, tool use, boundaries, and evaluation; otherwise, prepare a clearly hypothetical design discussion.
Ask targeted questions about the work
The role involves cross-functional requirements and lists Azure AI Studio, Azure OpenAI, Azure Cognitive Search, and Azure Machine Learning. Prepare questions about the first business use case, the existing Azure stack, evaluation expectations, and how teams handle production ownership.

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…