AI Full Stack Engineer lead

Innovisk India Private Limited; Mumbai; On-site; INR 1,500,000 - 3,000,000; Full time

Job summary

Ryan Specialty is seeking an AI Full Stack Engineer in Mumbai to build production-grade AI-powered web applications. You will design, develop, and deploy end-to-end solutions—from AI-driven backends and APIs to polished frontends—leveraging LLMs and agent frameworks.

Responsibilities include integrating LLM APIs (OpenAI, Azure OpenAI, Anthropic, Gemini), building REST/GraphQL endpoints, crafting responsive UIs with React/Next.js, and deploying on Azure or AWS using Docker and Kubernetes.

Qualifications

• Proficiency in Python (FastAPI/Flask) and JavaScript/TypeScript (React, Next.js, Node.js)
• Hands-on experience building or integrating AI Agents with LangChain, LangGraph, AutoGen, or CrewAI
• Experience calling and fine-tuning LLM APIs — OpenAI, Azure OpenAI, Anthropic, or Gemini
• Solid understanding of RAG pipelines, vector embeddings, and semantic search
• Proficiency with containerization (Docker) and cloud deployment (Azure or AWS)
• Experience with relational and NoSQL databases (PostgreSQL, MongoDB, Redis)
• Familiarity with REST API design and integration patterns
• Comfort using AI-assisted development tools (Copilot, Cursor, Claude Code) as day-to-day workflow

Responsibilities

• Design and develop full stack applications with AI-native features, integrating LLM APIs into both frontend and backend layers
• Develop RESTful and GraphQL APIs that expose AI agent capabilities
• Build responsive, modern UIs using React/Next.js that interact with AI backends in real-time
• Implement Retrieval-Augmented Generation (RAG) pipelines using vector databases for contextual AI apps
• Leverage AI coding assistants as core development tools to accelerate full-cycle engineering
• Containerize and deploy full stack AI applications to Azure/AWS using Docker, Kubernetes, and CI/CD
• Monitor, evaluate, and improve LLM-powered features through prompt engineering and feedback loops
• Collaborate with product, data, and DevOps teams to ship AI-powered features from prototype to production

Skills

Python

JS/TS

React

Next.js

Node.js

LLM APIs

LangChain

RAG

REST API

Prompt engineering

Tools

Docker

Kubernetes

PostgreSQL

MongoDB

Redis

OpenAI API

Azure OpenAI

Anthropic

Gemini

GitHub Copilot

Cursor

Claude Code

Job description

Position Summary: About the Role

We are looking for an AI Full Stack Engineer who can build complete, production-grade web applications powered by AI tools, LLMs, and autonomous AI Agents. You will design, develop, and deploy end-to-end solutions — from intelligent backend services and AI-driven APIs to polished, interactive frontends — leveraging the latest AI development platforms and agentic frameworks.

Location: Mumbai - India

What will your job entail?

Key Responsibilities

• Design and develop full stack applications with AI-native features, integrating LLM APIs (OpenAI, Azure OpenAI, Anthropic Claude) into both frontend and backend layers
• Develop RESTful and GraphQL APIs that expose AI agent capabilities to frontend clients and third-party systems
• Build responsive, modern UIs using React / Next.js that interact with AI backends in real-time (streaming responses, tool call results, agent progress)
• Implement Retrieval-Augmented Generation (RAG) pipelines using vector databases (Azure AI Search) for contextual AI applications
• Leverage AI coding assistants (GitHub Copilot, Cursor, Claude Code) as core development tools to accelerate full-cycle engineering work
• Containerize and deploy full stack AI applications to Azure / AWS using Docker, Kubernetes, and cloud-native CI/CD pipelines
• Monitor, evaluate, and improve LLM-powered features through prompt engineering, fine-tuning, and feedback loops
• Collaborate with product, data, and DevOps teams to ship AI-powered features from prototype to production

Required Skills

• Proficiency in Python (FastAPI / Flask) and JavaScript/TypeScript (React, Next.js, Node.js)
• Hands-on experience building or integrating AI Agents with frameworks like LangChain, LangGraph, AutoGen, or CrewAI
• Experience calling and fine-tuning LLM APIs — OpenAI, Azure OpenAI, Anthropic, or Gemini
• Solid understanding of RAG pipelines, vector embeddings, and semantic search
• Proficiency with containerization (Docker) and cloud deployment (Azure or AWS)
• Experience with relational and NoSQL databases (PostgreSQL, MongoDB, Redis)
• Familiarity with REST API design and integration patterns
• Comfort using AI-assisted development tools (Copilot, Cursor, Claude Code) as day-to-day workflow

Nice to Have

• Experience with Azure AI Foundry, Azure Machine Learning, or AWS Bedrock
• Knowledge of MLOps practices and model monitoring
• Exposure to multi-modal AI applications (vision, speech, document intelligence)
• Understanding of prompt engineering strategies, chain-of-thought, and function calling

Contributions to open-source AI/agent projects

Ryan Specialty is an Equal Opportunity Employer. We are committed to building and sustaining a diverse workforce throughout the organization. Our vision is an inclusive and equitable workplace where all employees are valued for and evaluated on their performance and contributions. Differences in race, creed, color, religious beliefs, physical or mental capabilities, gender identity or expression, sexual orientation, and many other characteristics bring together varied perspectives and add value to the service we provide our clients, trading partners, and communities. This policy extends to all aspects of our employment practices, including but not limited to, recruiting, hiring, discipline, firing, promoting, transferring, compensation, benefits, training, leaves of absence, and other terms, conditions, and benefits of employment.

Ryan Specialty, LLC and its affiliates (“Ryan Specialty”) do not accept unsolicited resumes or candidate profiles submitted by any staffing agencies, placement services or professional recruiters (“Agencies”), including any submissions made through our website or to email accounts of Ryan Specialty employees. Agencies must be registered in Ryan Specialty’s agency portal and have a fully executed contract for service between the Agency and the Agency. Agency fee agreements will only be valid if provided in such fully executed contract between the Agency. Any unsolicited resume or candidate profile received from an Agency without prior approval from Ryan Specialty’s HR department and in compliance with Ryan Specialty’s candidate submission process shall be considered unsolicited, gratuitous and property of Ryan Specialty for recruiting purposes and, as such, is not subject to payment of any Agency fees.