Gen AI Developer-Banglore,Pune,hyderabad,chennai

Intellics Global Services; Pune District, Chennai, Bengaluru; On-site; INR 1,200,000 - 2,400,000; Full time

Job summary

Intellics Global Services is seeking a Gen AI + Python Developer to design, build, and deploy generative AI solutions using LLMs, prompt engineering, and Python-based applications.

You will implement RAG pipelines, fine-tune and evaluate model outputs for relevance, and collaborate with Data Science, MLOps, and Product teams to deliver AI-driven features while ensuring scalable, maintainable code.

Qualifications

• Proficient in Python development.
• Experience with LLM frameworks (LangChain, LlamaIndex, Semantic Kernel).
• Knowledge of vector databases (Pinecone, FAISS, ChromaDB, Weaviate).
• Experience with REST API development (FastAPI/Flask).
• Understanding of prompt engineering & RAG architecture.
• Familiarity with cloud platforms (Azure/AWS/GCP).
• Exposure to Docker/Kubernetes is a plus.
• Experience with MLOps tools is desirable.

Responsibilities

• Design and develop Generative AI applications using LLMs (OpenAI, Azure OpenAI, Llama, Claude).
• Build and optimize Python-based backend services/APIs integrating AI models.
• Implement RAG pipelines using vector databases.
• Fine-tune and evaluate LLM outputs for accuracy and relevance.
• Work with prompt engineering techniques to optimize responses.
• Collaborate with Data Science, MLOps, Product teams to deliver AI features.
• Ensure code quality, scalability, and adherence to best practices.

Skills

Python

LLM frameworks

Vector databases

REST API

Prompt engineering

Cloud platforms

Docker/Kubernetes

Fine-tuning LLMs

MLOps tools

Tools

LangChain

LlamaIndex

Semantic Kernel

Pinecone

FAISS

ChromaDB

Weaviate

FastAPI

Flask

Job description

Role & responsibilities

Summary: We are looking for a Gen AI + Python Developer to design, build, and deploy generative AI solutions leveraging LLMs, prompt engineering, and Python-based application development.

Key Responsibilities:

• Design and develop Generative AI applications using LLMs (OpenAI, Azure OpenAI, Llama, Claude, etc.)
• Build and optimize Python-based backend services/APIs integrating AI models
• Implement RAG (Retrieval Augmented Generation) pipelines using vector databases
• Fine-tune and evaluate LLM outputs for accuracy, relevance, and performance
• Work with prompt engineering techniques to optimize model responses
• Collaborate with cross-functional teams (Data Science, MLOps, Product) to deliver AI-driven features
• Ensure code quality, scalability, and adherence to best practices

Must-Have Skills:

• Strong hands-on Python programming
• Experience with LLM frameworks (LangChain, LlamaIndex, Semantic Kernel)
• Working knowledge of vector databases (Pinecone, FAISS, ChromaDB, Weaviate)
• Experience with REST API development (FastAPI/Flask)
• Understanding of prompt engineering & RAG architecture
• Familiarity with cloud platforms (Azure/AWS/GCP)

Good to Have:

• Exposure to fine-tuning/training LLMs
• Experience with MLOps tools

Knowledge of Docker/Kubernetes