Full Stack AI Engineering Lead

Bloom AI; New Delhi; Hybrid; INR 1,500,000 - 2,800,000; Full time

Job summary

Bloom AI seeks a hands-on Full Stack AI Engineer with 4–6 years of experience to design, build and deploy production-grade AI applications. You will focus on multi-agent systems, backend engineering and end-to-end application development across enterprise data sources.

You will work across client engagements and Bloom AI capabilities, taking ownership from architecture through production deployment in a hybrid setup based in Delhi/NCR.

Qualifications

• 4–6 years of professional software engineering experience
• Strong proficiency in Python, backend engineering, API development
• Practical experience building agentic or multi-agent systems
• Experience with agent orchestration frameworks such as LangGraph, LangChain, CrewAI, AutoGen
• Strong understanding of LLM APIs, tool calling, RAG, embeddings, vector databases and context management
• Experience Developing full-stack applications using React or Next.js
• Strong SQL, database design and data integration fundamentals
• Familiarity with cloud infrastructure, Docker, Git, CI/CD and modern engineering practices

Responsibilities

• Design and develop multi-agent systems that coordinate specialized agents to execute complex tasks and workflows
• Implement agent orchestration, planning, tool calling, task delegation, context management and state management
• Build LLM-powered applications using frameworks such as LangGraph, LangChain, CrewAI, AutoGen or similar
• Develop retrieval-augmented generation (RAG), semantic search, agent memory and knowledge retrieval capabilities
• Integrate agents with enterprise APIs, databases, documents and external data sources
• Own features end-to-end, including technical design, development, testing, integration and deployment
• Deploy production-grade backend and full-stack applications

Skills

Python

AI/LLM apps

Agentic systems

React

Next.js

REST APIs

Cloud deployment

Docker

API development

Tools

LangGraph

LangChain

CrewAI

AutoGen

Azure OpenAI

Job description

Bloom AI builds AI-native intelligence systems and workflows for enterprise teams across research, marketing, sales and other knowledge-intensive functions. We combine enterprise data, external intelligence, AI and software engineering to help organizations build systems that continuously understand context, generate intelligence and support action. Our model sits between traditional product companies and services firms. We build reusable technology and engineering patterns while deploying them against real enterprise problems and adapting them to different client environments.

Bloom AI is based in the U.S. and India (Delhi/NCR). This is a hybrid role.

The Role

We are looking for a hands‑on Full Stack AI Engineer with 4–6 years of experience who can design, build and deploy production‑grade AI applications, with particular emphasis on multi-agent systems, backend engineering and end-to-end application development.

This is a core engineering role for someone who combines strong software fundamentals with practical experience building LLM-powered applications, agentic workflows and intelligent data systems.

You should be comfortable working across the stack—from building agent orchestration and backend services to developing user-facing applications, integrating enterprise data and deploying solutions in cloud environments.

This is not a prompt‑engineering or research‑only role. We are looking for someone who can turn AI capabilities into reliable, scalable software that solves real business problems.

You will work across client engagements, reusable Bloom AI capabilities and internal technology development, taking ownership of solutions from architecture through production deployment. You will be part of core team reporting to the CEO.

What You'll Do

Build Agentic Systems

• Design and develop multi-agent systems that coordinate specialized agents to execute complex tasks and workflows.
• Implement agent orchestration, planning, tool calling, task delegation, context management and state management.
• Build LLM-powered applications using frameworks such as LangGraph, LangChain, CrewAI, AutoGen or similar.
• Develop retrieval-augmented generation (RAG), semantic search, agent memory and knowledge retrieval capabilities.
• Integrate agents with enterprise APIs, databases, documents and external data sources.
• Implement evaluation, tracing, error handling, monitoring and reliability mechanisms for production AI systems.

Build Backend and Full Stack Applications

• Design and develop scalable backend services, REST APIs and application logic using Python and frameworks such as FastAPI.
• Build user-facing applications using modern frontend frameworks such as React, Next.js or similar.
• Develop data models, database integrations and processing pipelines for structured and unstructured data.
• Implement asynchronous processing, background jobs and integrations between application components.
• Design modular, maintainable architectures that support reuse across client environments.
• Own features end-to-end, including technical design, development, testing, integration and deployment.

Work with Graph and Context Systems

• Design data structures and retrieval mechanisms that help AI systems understand entities, relationships and context.
• Work with graph-based data models and knowledge graphs to represent relationships across enterprise and external data.
• Combine structured data, semantic search and graph-based retrieval to support richer agent reasoning and intelligence workflows.
• Contribute to the development of persistent context, memory and state-management capabilities for AI agents.
• Evaluate when relational databases, vector databases or graph-based approaches are appropriate for different problems.

Deploy Production Grade Systems

• Deploy and manage applications on cloud infrastructure, preferably Microsoft Azure, with AWS or GCP experience also relevant.
• Work with Azure OpenAI, Azure AI Foundry, model APIs and enterprise AI services.
• Implement containerization, CI/CD, authentication, logging and application monitoring.
• Build systems with appropriate security, access controls, data privacy and reliability standards.
• Debug performance, integration and production issues across the full application stack.
• Work with business and technical teams to understand workflows and translate requirements into working AI solutions.
• Rapidly prototype new capabilities, evaluate technical approaches and move successful prototypes into production.
• Integrate AI systems with existing enterprise applications, data sources and workflows.
• Collaborate with engineers to improve architecture, code quality and reusable components.
• Participate in client discussions, technical demonstrations and solution design.
  

What We're Looking For

• 4–6 years of professional software engineering experience, including hands‑on development of AI/LLM applications.
• Strong proficiency in Python, backend engineering, API development and software architecture.
• Practical experience building agentic or multi-agent systems, beyond basic chatbot or prompt-based applications.
• Experience with agent orchestration frameworks such as LangGraph, LangChain, CrewAI, AutoGen or similar.
• Strong understanding of LLM APIs, tool calling, RAG, embeddings, vector databases and context management.
• Experience developing full-stack applications, including working knowledge of React, Next.js or another modern frontend framework.
• Strong SQL, database design and data integration fundamentals.
• Working understanding of graph data structures, entity-relationship modeling and graph-based retrieval concepts.
• Experience taking applications from development through testing and production deployment.
• Familiarity with cloud infrastructure, Docker, Git, CI/CD and modern engineering practices.
• Strong problem-solving, debugging and independent execution skills.

Good to Have

• Start-up or 0->1 experience.
• Experience with Microsoft Azure, Azure AI Foundry or Azure OpenAI.
• Hands‑on experience with Neo4j, Amazon Neptune or other graph databases, including knowledge graph construction, Cypher and GraphRAG.
• Experience building stateful agents, long-running workflows, persistent memory or context-management systems.
• Familiarity with agent evaluation, observability and tracing tools such as LangSmith, Langfuse or similar.
• Experience with Model Context Protocol (MCP), event-driven architectures, queues or distributed systems.
• Experience integrating AI into enterprise applications such as CRM, marketing, sales or research workflows.
• Experience working directly with enterprise clients or in a fast-moving startup environment.