Role Overview
We are looking for an AI Engineer to build and maintain enterprise AI solutions using Generative AI, LLMs, RAG, Text-to-SQL, AI Agents, APIs, and governed enterprise data.
Responsibilities
- Develop centralized Enterprise AI and conversational AI platforms.
- Build Natural Language-to-SQL / Text-to-SQL solutions using governed data sources.
- Integrate AI applications with semantic layers, APIs, databases, and enterprise systems.
- Develop RAG-based solutions for documents, policies, manuals, and business knowledge.
- Design and implement AI agents and agentic workflows.
- Work with LLM platforms such as OpenAI, Azure OpenAI, Microsoft Copilot, Anthropic, and Gemini.
- Implement RBAC, authentication, authorization, data protection, audit logging, and AI security controls.
- Develop AI evaluation, monitoring, hallucination detection, and performance-improvement mechanisms.
- Support AI dashboards with KPIs, tables, charts, summaries, and analytics.
- Deploy and maintain AI applications using Azure/AWS/GCP, Docker, CI/CD, and monitoring tools.
- Ensure AI solutions use only approved, governed, read-only enterprise data sources.
Requirements
- Strong Python and SQL skills.
- Experience developing REST APIs and backend services.
- Hands-on experience with Generative AI, LLM APIs, Prompt Engineering, and Context Management.
- Practical experience in Text-to-SQL / Natural Language Query.
- Strong understanding of databases, data modelling, semantic layers, and metadata.
- Experience with RAG, embeddings, vector databases, and enterprise search.
- Experience with LangChain, LlamaIndex, Semantic Kernel, CrewAI, or similar frameworks.
- Experience with Azure/AWS/GCP and Docker.
- Understanding of AI security, RBAC, prompt injection, data leakage, and governance.
- 3–6 years of software/AI engineering experience.
- 1–2+ years of practical Generative AI/LLM development.
Skills
- Python
- SQL
- Generative AI
- LangChain
- Azure/AWS/GCP
Benefits
- Health insurance
- Provident Fund