AI Engineer

Kumaran Systems; Chennai; On-site; INR 1,200,000 - 1,800,000; Full time

Job summary

Kumaran Systems in Chennai is seeking an AI Engineer specialized in Python and Generative AI to design, develop, and deploy AI-driven solutions. You will work with LLMs, RAG pipelines, and AI application development across enterprise systems.

The role emphasizes hands-on experience with GenAI technologies, model fine-tuning, and integration with modern ML frameworks, with a strong focus on deploying scalable AI solutions from an office-based Chennai setup.

Qualifications

• 3+ years of AI/ML engineering experience with Python.
• Hands-on with Generative AI / LLMs (OpenAI GPT, Google Gemini, etc.).
• Practical RAG architecture, prompt engineering, and LLM fine-tuning.
• Familiarity with LangChain, LlamaIndex, Hugging Face, TensorFlow/PyTorch.
• Experience with Vector Databases (Pinecone, Chroma, FAISS, Weaviate).
• Strong NLP, ML, and DL fundamentals.
• Experience deploying models on AWS, Azure, or GCP.
• REST APIs, Docker, and basic MLOps practices.
• SQL/NoSQL databases understood; strong analytical skills.

Responsibilities

• Design, develop, and deploy AI/ML models and Generative AI apps using Python.
• Build and optimize RAG pipelines integrating LLMs with vector databases.
• Fine-tune and prompt-engineer LLMs for business use cases.
• Develop AI agents/chatbots and integrate with enterprise apps and APIs.
• Work with LangChain, LlamaIndex, and Hugging Face Transformers for GenAI solutions.
• Collaborate with Product, Data Engineering, and DevOps to scale AI solutions.
• Implement and manage vector databases (Pinecone, Chroma, FAISS, Weaviate).
• Evaluate models, test, and optimize for accuracy and latency.
• Stay updated on AI/GenAI advances and drive adoption where relevant.

Skills

Python

LLMs

RAG pipelines

Prompt engineering

NLP/DL concepts

Cloud platforms

REST APIs

Docker

MLOps basics

Education

Bachelor's/Master's in CS/AI/ML

Tools

LangChain

LlamaIndex

Hugging Face

TensorFlow

PyTorch

Pinecone

Chroma

FAISS

Weaviate

OpenAI

Google Gemini

Job description

AI Engineer - Python & Generative AI

Position: AI Engineer

Experience: 3- 6 Years

Location: Chennai

Work Mode: Work From Office

Employment Type: Full-Time

Function: Artificial Intelligence / Engineering

About the Role

We are looking for a skilled AI Engineer with strong hands-on experience in Python and Generative AI technologies to design, build, and deploy intelligent AI-driven solutions. The ideal candidate will have a solid foundation in machine learning concepts along with practical exposure to LLMs, RAG pipelines, and AI application development.

Key Responsibilities

• Design, develop, and deploy AI/ML models and Generative AI applications using Python.
• Build and optimize RAG (Retrieval-Augmented Generation) pipelines integrating LLMs with vector databases.
• Fine-tune and prompt-engineer LLMs (OpenAI, Mistral, Gemini, LLaMA, etc.) for specific business use cases.
• Develop AI agents/chatbots and integrate them with enterprise applications and APIs.
• Work with frameworks such as LangChain, LlamaIndex, and Hugging Face Transformers for GenAI solution development.
• Collaborate with cross-functional teams (Product, Data Engineering, DevOps) to build scalable AI solutions.
• Implement and manage vector databases (Pinecone, Chroma, FAISS, Weaviate, etc.).
• Conduct model evaluation, testing, and performance optimization for accuracy and latency.
• Stay updated with the latest advancements in AI/ML and Generative AI technologies and recommend adoption where relevant.
• Ensure best practices in code quality, version control, and documentation.

Required Skills & Qualifications

• 3+ years of overall experience in AI/ML engineering, with strong proficiency in Python.
• Hands-on experience with Generative AI / LLMs (OpenAI GPT, Google Gemini, Anthropic Claude, Mistral, LLaMA, etc.).
• Practical experience with RAG architecture, prompt engineering, and LLM fine-tuning.
• Familiarity with AI/ML frameworks: LangChain, LlamaIndex, Hugging Face, TensorFlow/PyTorch.
• Experience working with Vector Databases (Pinecone, Chroma, FAISS, Weaviate, etc.).
• Strong understanding of NLP, Machine Learning, and Deep Learning concepts.
• Experience with cloud platforms (AWS, Azure, or GCP) for AI model deployment.
• Familiarity with REST APIs, containerization (Docker), and basic MLOps practices.
• Good understanding of SQL/NoSQL databases.
• Strong analytical, problem-solving, and communication skills.

Good to Have

• Experience with AI Agent frameworks (Agent SDKs, AutoGen, CrewAI, etc.).
• Exposure to Kubernetes and CI/CD pipelines.
• Prior experience in building chatbots, virtual assistants, or automation solutions.
• Knowledge of AI governance, responsible AI, and model evaluation frameworks.

Education

• Bachelor's/Master's degree in Computer Science, Information Technology, AI/ML, or a related field.

Work Mode

Work From Office Chennai