AI Engineer

Ellume Technologies; Mumbai; On-site; INR 2,500,000 - 4,000,000; Full time

Job summary

Ellume Technologies in Mumbai is seeking an experienced AI Engineer to build, deploy, and monitor scalable AI and Generative AI systems across the full lifecycle, from data processing to production support. You will design reliable AI systems using LLMs, RAG pipelines, embeddings, and prompt engineering, focusing on retrieval quality, latency, and scalability.

You will collaborate with product managers and backend teams to integrate models into Ellume's renewable energy and EPC software

Qualifications

• Experience across the complete AI lifecycle from development to production.
• Proficiency in Python with deep learning frameworks (PyTorch or TensorFlow).
• Experience with LLM orchestration using LangChain or LlamaIndex, plus vector databases and RAG pipelines.

Responsibilities

• Build, deploy, optimise, and monitor scalable, production-grade AI systems across the full lifecycle — data processing through production support.
• Design and execute reliable AI systems using LLMs, RAG pipelines, embeddings, vector databases, and prompt engineering.
• Architect robust AI systems focusing on retrieval quality, latency, scalability, and high-performance post-deployment.
• Write clean, maintainable, system-driven code with feature engineering and inference optimisation aligned to product goals.
• Partner with product managers and backend engineers to integrate AI models into Ellume's software ecosystems.

Skills

Python

Deep learning

LLMs

LangChain

LlamaIndex

Vector DB

RAG pipelines

MLOps

System design

Problem solving

Tools

PyTorch

TensorFlow

LangChain

LlamaIndex

Vector DB

Job description

At Ellume, we are pioneering the future of clean power. We operate across three verticals—Renewable Energy, Independent Power Production (IPP), Engineering, Procurement & Construction (EPC), and Technology—committed to driving innovation across the renewable sector.

Responsibilities

• Build, deploy, optimise, and monitor scalable, production-grade AI and Generative AI systems across the full lifecycle — data processing through production support.
• Design and execute reliable AI systems utilising Large Language Models (LLMs), RAG pipelines, embeddings, vector databases, and prompt engineering.
• Architect robust AI systems with a strict focus on retrieval quality, latency optimisation, scalability, and high-performance post-deployment.
• Write exceptionally clean, maintainable, and system-driven code, ensuring feature engineering and inference optimisation align with core product goals.
• Partner with product managers and backend engineering teams to integrate AI models into Ellume's renewable energy and EPC software ecosystems.

Requirements

• Proven hands-on expertise across the complete AI lifecycle, taking AI models from development to scalable production environments.
• Strong proficiency in Python and practical experience with deep learning frameworks such as PyTorch or TensorFlow.
• Deep understanding of machine learning fundamentals, neural networks, model evaluation, feature engineering, inference optimisation, and scalable AI architectures.
• Direct experience with LLM orchestration frameworks such as LangChain or LlamaIndex, alongside vector databases and RAG pipelines.
• Sharp engineering instinct, ownership mindset, excellent problem-solving abilities, and a system-oriented approach to development.
• Bonus: familiarity with time-series data and anomaly detection, autonomous AI agents, MLOps practices, and prior experience in Renewable Energy, Utilities, or EPC sectors.

Proven hands-on expertise across the complete AI lifecycle, taking AI models from development to scalable production environments. Strong proficiency in Python and practical experience with deep learning frameworks such as PyTorch or TensorFlow. Deep understanding of machine learning fundamentals, neural networks, model evaluation, feature engineering, inference optimisation, and scalable AI architectures. Direct experience with LLM orchestration frameworks such as LangChain or LlamaIndex, alongside vector databases and RAG pipelines. Sharp engineering instinct, ownership mindset, excellent problem-solving abilities, and a system-oriented approach to development. Bonus: familiarity with time-series data and anomaly detection, autonomous AI agents, MLOps practices, and prior experience in Renewable Energy, Utilities, or EPC sectors.