AI ENGINEER

Job Summary

We are looking for an AI Engineer to design, build, and continuously improve an AI-powered assistant embedded within our web applications and customer portals.

The role combines software engineering, Generative AI, LLMs, RAG, Azure OpenAI, API development, AI orchestration, security, and evaluation. The ideal candidate will have hands-on experience building production-grade AI applications and will be responsible for ensuring that AI responses are accurate, secure, relevant, and grounded in enterprise data.

Key Responsibilities

- Build, enhance, and maintain AI assistants and personalization capabilities integrated with React-based web applications.
- Design and develop the AI orchestration layer that determines what information, context, and instructions are provided to LLMs.
- Develop and implement Retrieval-Augmented Generation (RAG) solutions using Azure OpenAI and enterprise data sources.
- Build workflows that enable AI assistants to retrieve relevant information and generate accurate, context-aware responses.
- Implement AI guardrails and validation mechanisms for both input and output.
- Ensure data privacy, security, access control, and tenant isolation in multi-tenant AI applications.
- Develop mechanisms to prevent sensitive or customer-specific information from being exposed across tenants.
- Integrate Azure OpenAI / LLM APIs into enterprise applications.
- Develop backend services and APIs using Python and FastAPI.
- Work with vector databases, embeddings, semantic search, and retrieval pipelines.
- Implement monitoring for LLM latency, token consumption, cost, throughput, and reliability.
- Develop and maintain LLM evaluation frameworks and test suites to measure response quality, accuracy, relevance, and safety.
- Collaborate with Data Scientists, Backend Engineers, Data Engineers,



and Product teams to ensure AI solutions are supported by high-quality, structured, and privacy-compliant data.
- Continuously experiment with and improve prompts, RAG strategies, orchestration, model selection, and AI response quality.
- Contribute to the design of scalable, reliable, and production-ready Generative AI applications.

Required Technical Skills

Mandatory Skills

- 7+ years of overall software engineering experience.
- Minimum 2+ years of hands-on experience with AI, Generative AI, LLMs, or enterprise prompt engineering.
- Strong programming skills in Python.
- Hands-on experience developing APIs using FastAPI.
- Experience working with Azure OpenAI or similar LLM platforms.
- Hands-on understanding of Large Language Models (LLMs) and Generative AI applications.
- Experience with Retrieval-Augmented Generation (RAG) architectures and workflows.
- Experience with Vector Databases / Vector Search.
- Understanding of embeddings, semantic search, prompt engineering, and context management.
- Exposure to LLM evaluation frameworks and AI response evaluation.
- Understanding of AI application security, data privacy, and responsible AI principles.

Valuable to Have

- Experience building enterprise-grade AI assistants or chatbots.
- Experience with multi-tenant SaaS applications.
- Experience with LLM observability and monitoring.
- Knowledge of AI guardrails, content filtering, hallucination mitigation,



and prompt injection protection.
- Experience with Azure cloud services.
- Familiarity with React or other modern frontend frameworks.
- Experience with AI/ML application deployment and CI/CD.
- Experience with RAG frameworks such as LangChain, LlamaIndex, Semantic Kernel, or equivalent.
- Experience with vector databases such as Azure AI Search, Pinecone, Weaviate, Qdrant, or similar.

Key Competencies Generative AI / LLM Application Development | AI Orchestration | Retrieval-Augmented Generation (RAG) | Prompt Engineering | Azure OpenAI | Python | FastAPI | Vector Databases | Embeddings & Semantic Search | LLM Evaluation | AI Guardrails | AI Security & Data Privacy | Multi-Tenant AI Applications | LLM Observability | API Development

Technology Stack

Azure OpenAI | Python | FastAPI | RAG | Vector Databases | LLMs | Prompt Engineering | Embeddings | Semantic Search | LLM Evaluation Frameworks | React | Azure

Ideal Candidate The ideal candidate is a hands-on AI Engineer / GenAI Engineer who can take an AI use case from concept through production. You should be comfortable writing code, integrating LLMs, designing RAG pipelines, working with enterprise data, implementing AI guardrails, and measuring the quality and cost of AI applications.

You should be interested in building reliable, secure, production-grade AI systems, rather than simply integrating an LLM API.

Key Skills / Search Keywords

AI Engineer, Generative AI, GenAI, LLM, Azure OpenAI, OpenAI, Python, FastAPI, RAG, Retrieval Augmented Generation, Prompt Engineering, Vector Database, Vector Search, Embeddings, Semantic Search, LLM Evaluation, AI Guardrails, LLM Observability, Azure, REST API, LangChain, LlamaIndex, Semantic Kernel, AI Chatbot

📌 Artificial Intelligence Engineer (Bengaluru)
🏢 dSights
📍 Bengaluru