Python ML /GenAI

Sallybase; Gurgaon; Hybrid; INR 900,000 - 1,800,000; Full time

Job summary

Sallybase is hiring a capable AI Software Engineer to develop and maintain Generative AI applications in Python. You will build AI-powered chatbots and automation, integrating multiple LLMs and RAG architectures.

You will work with LangChain and LlamaIndex, design prompts, and develop REST APIs for AI services. Ideal candidates have strong Python skills, experience with OpenAI/Azure APIs, cloud familiarity (Azure/AWS/GCP), and Git proficiency.

Qualifications

• Strong Python programming skills.
• Solid understanding of Generative AI concepts and LLMs.
• Experience with OpenAI/Azure OpenAI APIs.
• Hands-on with LangChain, LlamaIndex, or similar.
• Knowledge of RAG architectures and vector databases.
• Experience building REST APIs using FastAPI or Flask.
• Familiarity with Git version control.
• Exposure to cloud platforms like Azure, AWS or GCP.

Responsibilities

• Develop and maintain Generative AI applications using Python.
• Build AI-powered chatbots, virtual assistants, and automation solutions.
• Integrate LLMs (OpenAI, Azure OpenAI, Claude, Gemini, Llama, etc.) into apps.
• Design and optimize prompts for model performance.
• Implement retrieval-augmented generation using vector stores.
• Work with LangChain, LlamaIndex, and similar frameworks.
• Develop REST APIs and integrate AI services with web apps.
• Collaborate with cross-functional teams; perform testing and optimization.

Skills

Python

Generative AI concepts

LLMs

Prompt engineering

REST APIs

Git

Cloud platforms (Azure/AWS/GCP)

Tools

LangChain

LlamaIndex

RAG architecture

Vector databases (Pinecone, ChromaDB, FAISS)

Azure OpenAI/OpenAI APIs

FastAPI/Flask

Job description

Responsibilities

Develop and maintain Generative AI applications using Python. Build AI-powered chatbots, virtual assistants, and automation solutions. Integrate Large Language Models (OpenAI, Azure OpenAI, Claude, Gemini, Llama, etc.) into applications. Design and optimize prompts to improve model performance and accuracy. Implement Retrieval-Augmented Generation (RAG) solutions using vector databases. Work with frameworks like LangChain, LlamaIndex, and Semantic Kernel. Develop REST APIs and integrate AI services with web applications. Collaborate with cross-functional teams to understand business requirements and deliver AI-driven solutions. Perform testing, debugging, and performance optimization of AI applications.

Technical and Professional Requirements:

Strong proficiency in Python programming. Knowledge of Generative AI concepts, LLMs, and Prompt Engineering. Experience with OpenAI/Azure OpenAI APIs. Hands-on experience with LangChain, LlamaIndex, or similar frameworks. Knowledge of RAG Architecture and vector databases such as Pinecone, ChromaDB, FAISS, or Azure AI Search. Experience with REST APIs, FastAPI, or Flask. Understanding of Git and version control systems. Familiarity with cloud platforms such as Azure, AWS, or GCP.

Preferred Skills:

• Technology->AI-Data science->PYTHON - AI-Data Science
• Technology->AI-Data science->Machine Learning
• Technology->AI-Generative AI->Generative AI for Data Analytics