Senior Generative AI Engineer

Senior Generative AI Engineer

Location: Bangalore, India
Experience: 5+ years
Employment Type: Full-time

Role Summary

We are looking for a Senior Generative AI Engineer to design, build, test, and deploy enterprise-grade AI solutions using LLMs, Generative AI, RAG, AI agents, MLOps, and cloud platforms.

The ideal candidate should have a strong software engineering background, hands-on AI/ML experience, and a quality-first mindset to build secure, scalable, reliable, and production-ready AI applications.

Key Responsibilities

• Build AI-powered applications such as AI copilots, chatbots, assistants, document intelligence solutions, and automation agents.
• Design and develop solutions using LLMs, RAG, prompt engineering, context engineering, embeddings, and vector databases.
• Build agentic AI workflows using tools such as LangChain, LangGraph, Semantic Kernel, CrewAI, AutoGen, or similar frameworks.
• Develop, fine-tune, evaluate, and deploy AI/ML models.
• Implement MLOps/LLMOps pipelines for model deployment, monitoring, versioning, and lifecycle management.
• Create APIs, microservices, and cloud-native AI applications.
• Design and execute testing strategies for AI applications, including prompt testing, LLM evaluation, hallucination detection, bias testing, regression testing, and security testing.
• Monitor AI systems for performance, drift, accuracy, latency, cost, and reliability.
• Ensure AI solutions follow Responsible AI, security, privacy, governance, and compliance standards.
• Work closely with product, engineering, QA, cloud, security, and business teams.

Required Qualifications

• Bachelors or Masters degree in Computer Science, AI/ML, Data Science, Engineering, or related field.
• 5+ years of software engineering experience.
• Hands-on experience in AI/ML, Generative AI, LLMs, RAG, or MLOps.
• Strong programming experience in Python; experience with Java, C#, JavaScript/TypeScript, or SQL is a plus.
• Experience building production-grade applications, APIs, microservices, or cloud-based systems.
• Good understanding of SDLC, STLC, QA automation, deployment, monitoring, and production support.

Mandatory Technical Skills

Programming

• Python
• Java / C# / JavaScript / TypeScript
• SQL
• REST APIs
• Microservices

Generative AI & LLMs

• GPT, Claude, Gemini, Llama, Mistral, or similar models
• Prompt engineering
• RAG
• Embeddings
• Vector databases
• LLM evaluation
• Fine-tuning

AI Frameworks

• LangChain
• LangGraph
• Semantic Kernel
• LlamaIndex
• CrewAI
• AutoGen
• Hugging Face

MLOps / LLMOps

• MLflow
• Kubeflow
• Airflow
• CI/CD pipelines
• Model registry
• Model monitoring
• Docker
• Kubernetes

QA & Testing

• Selenium
• Playwright
• Cypress
• PyTest
• JUnit
• API testing
• Performance testing
• AI model testing
• Prompt testing
• Hallucination and bias testing

Cloud

• Azure / Azure OpenAI
• AWS / Bedrock / SageMaker
• GCP / Vertex AI

Preferred Skills

• Multi-agent systems
• GraphRAG
• Knowledge graphs
• Multi-modal AI
• Synthetic data generation
• AI observability
• Human-in-the-loop workflows
• Responsible AI and AI governance
• Prompt injection and jailbreak testing
• Enterprise search and document intelligence

AI Quality Engineering Expectations

The candidate should be able to:

• Test LLM responses for accuracy, relevance, safety, and consistency.
• Build automated evaluation pipelines for prompts, RAG, and agent workflows.
• Measure hallucination, bias, toxicity, groundedness, and response quality.
• Create golden datasets and regression test suites.
• Validate AI systems for security, privacy, fairness, and compliance.
• Integrate AI quality checks into CI/CD pipelines.

Tools & Technologies

• AI/LLM: OpenAI, Azure OpenAI, Claude, Gemini, Llama, Hugging Face
• Frameworks: LangChain, LangGraph, Semantic Kernel, LlamaIndex, CrewAI, AutoGen
• Vector DB: Pinecone, Weaviate, FAISS, ChromaDB, Milvus, Azure AI Search
• MLOps: MLflow, Kubeflow, Airflow, Docker, Kubernetes
• Testing: Selenium, Playwright, Cypress, PyTest, JUnit, Postman, JMeter
• Cloud: Azure, AWS, GCP
• Monitoring: Prometheus, Grafana, Azure Monitor, CloudWatch, LangSmith

Success Metrics

• Quality and reliability of AI solutions delivered.
• Reduction in hallucination and AI response errors.
• Improved model accuracy and evaluation scores.
• Faster deployment of AI solutions to production.
• Better automation coverage and reduced manual effort.
• Improved system uptime, latency, and cost efficiency.
• Strong compliance with Responsible AI and security standards.
• Measurable business impact from AI solutions.