Analista desarrollador 3

Michelin Oy; Pune District; On-site; INR 1,500,000 - 2,400,000; Full time

Job summary

Michelin Oy in Pune, India is seeking a backend engineer to move AI exploration into production. You will design and build GenAI powered applications, integrate LLMs, embeddings, and RAG components, and deliver robust AI capabilities deployed in enterprise systems.

The role requires strong Python/Node.js/Java, experience with LangChain, LlamaIndex, Hugging Face, OpenAI API, and hands-on cloud work (Azure, AWS, or GCP).

Qualifications

• Backend engineering experience in Python, Node.js or Java.
• Proficiency with GenAI frameworks and APIs.
• Hands-on cloud platform experience (Azure, AWS or GCP).
• Ability to operate in large enterprise ecosystems with strong service mindset.

Responsibilities

• Design and develop AI-powered applications using LLMs, embeddings, and RAG.
• Define scalable GenAI architectures with robustness and security.
• Implement APIs, microservices, and AI pipelines in an industrial cloud environment.
• Support client teams with architecture reviews, audits and best practices.
• Ensure solution quality, security, compliance and observability.

Skills

Python

Node.js

Java

LangChain

LlamaIndex

Hugging Face

OpenAI API

Azure

AWS

GCP

RAG architectures

Vector databases

MLOps pipelines

Tools

LangChain

LlamaIndex

Hugging Face

OpenAI API

Job description

MissionMove from AI exploration to AI adoption by accelerating the software development lifecycle through measurable impact, real usage, and scaled adoption—delivering tangible results powered by the DRIVE program. **Key Expected Achievements**As part of a strategic initiative on Generative AI, you will design, build, and industrialize high visibility GenAI solutions. You will work closely with innovation, data, and IT teams to deliver robust, scalable, and secure AI capabilities that integrate seamlessly with enterprise systems**Key Responsibilities:**• Design and develop AI powered applications integrating Large Language Models (LLMs), including RAG, embeddings, and agent-based components.• Define and contribute to scalable GenAI architectures, ensuring robustness, performance, and industrial readiness.• Implement APIs, microservices, and AI pipelines within an industrial cloud environment.• Support client teams through scoping, technical expertise, architecture reviews, audits, and best practice guidance.• Ensure solution quality, security, compliance, and observability, following governance and risk management standards. **Required Profile:**• Strong backend engineering experience in Python, Node.js, or Java.• Proficiency with GenAI frameworks such as LangChain, LlamaIndex, Hugging Face, and OpenAI API.• Hands on exposure to at least one major cloud platform (Azure, AWS, or GCP) and experience with demanding production grade industrial environments.• Ability to operate effectively in large enterprise ecosystems: structured communication, rigor, and a strong service mindset.• Experience with RAG architectures, vector databases, and MLOps pipelines is a strong plus. **Team Life & Ways of Working:**• Embrace and respect Agile rituals, contributing actively to continuous improvement of team processes and collaboration.• Participate in workload estimation for backlog items, challenging complexity and scope when needed.• Contribute to sprint planning and allocation of tasks, supporting the delivery of incremental value and modernization of components (Evergreen approach). **Behavioural Skills:**Planning & organizing,Teamwork & Collaboration,**Customer Focus,**Continuous learningAbility to rapidly learn and take advantage of new concepts, business models, and technologies**Working with internal and external stakeholders in an international environment.**Product approach mindset Experience - 5-7 years