# AI Engineer / Data Scientist - GenAI & Agentic AI

- Experience : 5-7 Years

- Location : Bangalore

- Joining : Immediate to 15 Days

- Job Summary :

We are looking for a hands-on - AI Engineer / Data Scientist- with strong experience in - Generative AI, Agentic AI, LLMs, RAG, and Python- to design, develop, deploy, and optimize production-grade AI applications.

The ideal candidate should have practical experience building - agentic workflows, RAG-based solutions, enterprise AI applications, and LLM-powered automation- , along with strong exposure to the - Azure AI ecosystem, Databricks, MLflow, and Kubernetes- .

Key Responsibilities :

- Design and develop production-ready - Generative AI and Agentic AI applications- for enterprise use cases.

- Build intelligent agent workflows using frameworks such as - LangGraph, AutoGen, CrewAI, Semantic Kernel, or PydanticAI .

- Develop advanced - RAG pipelines- including document ingestion, chunking, embeddings, vector search, hybrid search, re-ranking, memory, and tool orchestration.

- Integrate - LLMs- such as GPT, Claude, LLaMA, and other foundation models into enterprise applications.

- Develop - multi-agent and tool-using AI systems- capable of executing complex enterprise workflows.

- Implement prompt engineering techniques to improve accuracy, reliability, and performance.

- Develop AI solutions using - Azure OpenAI, Azure AI Search, and Azure AI Services- .

- Build and manage ML/AI workflows using - Databricks, MLflow, and Delta Lake- .

- Develop REST APIs, WebSockets, and event-driven services to integrate AI applications with enterprise systems.

- Deploy containerized AI workloads using - Docker and Kubernetes- , including - Azure AKS/ARO- .

- Implement CI/CD pipelines using - Jenkins, GitHub Actions, or similar tools- .

- Implement responsible AI practices, including - guardrails, content filtering, prompt-injection protection, and secure AI interactions- .

- Develop evaluation frameworks and metrics to measure - task success, response quality, hallucination, latency, reliability, and cost- .

- Monitor and troubleshoot AI applications in production environments.

- Optimize LLM applications for scalability, performance, latency, reliability, and cost.

- Collaborate with Data Scientists, ML Engineers, Cloud Engineers, DevOps teams, and business stakeholders.

- Follow - SDLC, Agile, version control, testing, documentation, and production deployment