Generative AI Engineer

Job Title: Data Scientist RAG & Edge AI Systems

• Location: Chennai
• Experience: 3+ years
• Joining: Immediate to 30 days preferred

About the Role

We are seeking a Data Scientist with strong experience in RAG (Retrieval-Augmented Generation), LLMs, and Edge AI processing to join our growing AI engineering team.

This role combines hands-on engineering with strategic AI design

Key Responsibilities

• Design and develop LLM and RAG-based systems that enhance knowledge discovery, automation, and decision support.
• Build and orchestrate end-to-end AI pipelines using Azure AI Studio, Logic Apps, and Data Factory.
• Develop APIs and microservices for AI model integration with business and plant systems.
• Optimize and deploy deep learning models to edge devices (e.g., NVIDIA Jetson, AI PCs) for real-time inference.
• Fine-tune LLMs for domain-specific tasks, balancing accuracy, speed, and compute efficiency.
• Collaborate cross-functionally with data engineers, software developers, and domain experts to bring AI prototypes to production.
• Monitor model performance, automate retraining pipelines, and ensure compliance with data governance and security standards.

Required Skills & Experience

• RAG & LLMs: Experience building Retrieval-Augmented Generation systems using frameworks such as LangChain, LlamaIndex, or Azure OpenAI Service.
• Azure Stack: Hands-on experience with Azure AI Studio, Azure Machine Learning, Logic Apps, Functions, and Data Factory.
• Programming: Strong proficiency in Python, with experience in PyTorch, TensorFlow, LangChain, and FastAPI.

Edge AI Processing:

• Deploying and optimizing models on edge devices such as NVIDIA Jetson, Intel AI PCs, or ARM-based systems.
• Proficiency in TensorRT for real-time inference.
• Familiarity with Docker and remote monitoring for distributed edge workloads.
• Data Handling: Experience with SQL and vector databases for retrieval and embedding management.
• Visualization & Monitoring: Experience building dashboards using Power BI, Streamlit, or similar tools for inference metrics and explainability.

Preferred / Nice-to-Have

• Strong understanding of vector search optimization, document embeddings, and semantic retrieval at scale.
• Experience with multimodal AI systems (text and image) for industrial or enterprise use.
• Understanding of model compression, quantization, and GPU optimization for on-device AI.
• Experience integrating AI models with manufacturing systems (MES, SCADA, or PLC data).
• Familiarity with Elixir/Phoenix for chatbot or API integration within enterprise platforms.
• Awareness of AI safety, ethical AI, and data privacy frameworks in regulated environments.