Generative AI Engineer

Navlakha Management Services; Mumbai; On-site; INR 1,400,000 - 2,600,000; Full time

Job summary

Navlakha Management Services in Mumbai seeks a Generative AI Engineer to design, develop, integrate, and deploy GenAI solutions for enterprise use cases. You will work with GenAI, LLMs, RAG, Python, embeddings, and vector databases to create scalable AI applications.

You will collaborate with Data, Cloud, and Software teams, implement Azure OpenAI/OpenAI APIs, and ensure security, governance, and responsible AI practices across deployments.

Qualifications

• Generative AI experience with hands-on implementation.
• Strong knowledge of LLMs, embeddings, and prompt engineering.
• Experience building production-grade AI applications and pipelines.

Responsibilities

• Develop and deploy Generative AI / LLM-based applications.
• Build RAG pipelines using enterprise data.
• Work with LLMs, prompt engineering, embeddings, and vector databases.
• Develop AI solutions using Python and AI/ML frameworks.
• Integrate Azure OpenAI / OpenAI APIs and other GenAI services.
• Develop and optimize AI agents and intelligent automation.
• Implement data ingestion, preprocessing, chunking, embedding, and retrieval workflows.
• Evaluate LLM performance, response quality, accuracy, and latency.
• Collaborate with Data Engineering, Cloud, Software Engineering, and business teams.
• Deploy and monitor GenAI applications in cloud environments.
• Follow security, governance, scalability, and responsible AI practices.

Skills

GenAI

LLMs

RAG

Python

Prompt engineering

Embeddings

Vector databases

AI app development

Azure OpenAI

OpenAI APIs

AI agents

Automation

Tools

Azure OpenAI

Job description

Job Description

We are looking for a Generative AI Engineer with strong hands-on experience in GenAI, Large Language Models (LLMs), RAG, Python, and AI application development. The candidate will be responsible for designing, developing, integrating, and deploying GenAI solutions for enterprise use cases.

Key Responsibilities

• Develop and deploy Generative AI / LLM-based applications.
• Build RAG (Retrieval-Augmented Generation) pipelines using enterprise data.
• Work with LLMs, prompt engineering, embeddings, and vector databases.
• Develop AI solutions using Python and relevant AI/ML frameworks.
• Integrate Azure OpenAI / OpenAI APIs and other GenAI services.
• Develop and optimize AI agents and intelligent automation solutions.
• Implement data ingestion, preprocessing, chunking, embedding, and retrieval workflows.
• Evaluate LLM performance, response quality, accuracy, and latency.
• Collaborate with Data Engineering, Cloud, Software Engineering, and business teams.
• Deploy and monitor GenAI applications in cloud environments.
• Follow security, governance, scalability, and responsible AI practices.