Location Name: Pune Corporate Office - Mantri
Job Purpose
We are looking for a skilled AI Engineer to design, build, and deploy Generative AI solutions using Large Language Models (LLMs) such as GPT and Gemini. The ideal candidate has strong experience in prompt engineering, Python development, Retrieval-Augmented Generation (RAG), and deploying scalable AI applications on Linux servers and Azure Kubernetes Service (AKS).
Duties And Responsibilities
Key Responsibilities
- Design, develop, and deploy AI applications using GPT, Gemini, and other LLMs
- Create and optimize prompt engineering strategies for reliable and high-quality outputs
- Build and maintain RAG pipelines using embeddings and vector databases
- Develop backend services and APIs using Python
- Deploy, manage, and optimize AI applications on Linux servers
- Containerize applications and deploy them on AKS
- Monitor system performance, scalability, and cost
- Implement security, access control, and data privacy best practices
Required Qualifications And Experience
- Hands-on experience with GPT, Gemini, or similar LLM platforms
- Strong expertise in prompt writing and prompt optimization
- Solid experience with RAG (Retrieval-Augmented Generation) architectures
- Proficiency in Python
- Experience with vector databases (Azure Cognitive Search, Pinecone, FAISS, etc
- Strong knowledge of Linux server environments
- Experience deploying applications on AKS (Azure Kubernetes Service)
- Familiarity with Git and CI/CD pipelines
Preferred / Nice-to-Have
- Experience with Azure OpenAI / Azure AI services
- Knowledge of Docker and Kubernetes internals
- Experience with monitoring tools (Azure Monitor)
- Exposure to LLM fine-tuning and evaluation
