Senior Software Engineer (Full Stack AI Engineer)

Icube Consulting Services; Bengaluru; On-site; INR 4,000,000 - 7,000,000; Full time

Job summary

Icube Consulting Services in Bengaluru is seeking a Senior Software Engineer (Full Stack AI Engineer) to design, build, and deploy scalable AI-powered applications for enterprise use cases.

You will work across the full stack—Python back-end, modern front-end, and AI orchestration—delivering production-ready solutions with robust testing, CI/CD, and observability.

Qualifications

• Bachelor's or Master's degree in Computer Science, Information Technology, Engineering, Artificial Intelligence, or a related discipline
• Strong hands‑on experience with Python
• Strong experience building production‑grade web applications and APIs using FastAPI, Flask, Node.js/Express, React.js, or Next.js
• Practical experience building applications using Generative AI and LLMs
• Hands‑on experience with Agentic AI, LLM orchestration, RAG, tool calling, and multi‑agent workflows
• Experience with one or more AI frameworks such as LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen, or equivalent
• Experience working with vector databases / vector search technologies and embeddings
• Strong understanding of SQL and relational databases; NoSQL experience is a plus
• Experience with REST APIs, microservices, asynchronous processing, and distributed architectures
• Experience with at least one major cloud platform, preferably Azure or AWS
• Hands‑on experience with Docker and familiarity with Kubernetes and CI/CD practices
• Strong understanding of Git, Agile development, testing, debugging, and software engineering best practices
• Strong analytical, problem‑solving, communication, and collaboration skills

Responsibilities

• Design and implement LLM-powered applications, agentic AI workflows, and multi-agent systems
• Build AI agents using LangChain, LangGraph, CrewAI, AutoGen or equivalents
• Develop RAG pipelines using embeddings, vector search, and knowledge bases
• Design prompting, tool calling, memory, orchestration, and workflow patterns
• Integrate LLMs and enterprise services like Azure OpenAI, Azure AI, AWS Bedrock
• Evaluate AI solutions for accuracy, latency, cost, reliability, and hallucination reduction
• Implement guardrails, validation, observability, and human-in-the-loop mechanisms
• Design and develop scalable AI-powered apps with Python, FastAPI, React/Next.js/Node.js
• Develop REST APIs, microservices, and AI orchestration layers
• Build web interfaces for AI features like assistants, chatbots, search, analytics
• Integrate AI services into existing enterprise apps

Skills

Python

Full-stack development

AI frameworks

LLM orchestration

RAG

Vector databases

Cloud platforms

Docker

Kubernetes

Git & Agile

REST APIs

CI/CD

Testing & debugging

Communication & collaboration

Education

Bachelor's or Master's degree in Computer Science, Information Technology, Engineering, Artificial Intelligence, or a related discipline

Tools

FastAPI

Flask

Node.js/Express

React.js

Next.js

LangChain

LangGraph

LlamaIndex

CrewAI

AutoGen

Pinecone

Weaviate

Milvus

Azure OpenAI

Azure AI Search

AWS Bedrock

Docker

Kubernetes

Git

Airflow

Job description

Job Title

Senior Software Engineer (Full Stack AI Engineer)

Location

Basawanagudi, Bangalore

Duration

Full Time Employee

Client

Internal Project/Internal Position

Full Stack AI Engineer

Role Overview

We are looking for a Full Stack AI Engineer to design, build, and deploy scalable, production-ready AI applications for enterprise use cases.

The ideal candidate combines strong Python and full-stack engineering skills with hands-on experience in Generative AI, Agentic AI, RAG, LLM orchestration, and AI-enabled application development. You will work across the complete application lifecycle—from solution design and AI workflow development to backend APIs, user interfaces, cloud deployment, and production optimization.

This role is ideal for an engineer who enjoys solving complex problems, experimenting with emerging AI technologies, and turning AI capabilities into reliable, scalable business applications.

Key Responsibilities

AI & Agentic AI Engineering

• Design and implement LLM-powered applications, Agentic AI workflows, and multi-agent systems.
• Build and orchestrate AI agents using frameworks such as LangChain, LangGraph, CrewAI, AutoGen, or equivalent technologies.
• Develop RAG (Retrieval-Augmented Generation) pipelines using embeddings, vector search, document processing, and knowledge bases.
• Design effective prompting, tool calling, memory, agent orchestration, and workflow patterns.
• Integrate LLMs and enterprise AI services such as Azure OpenAI, Azure AI, AWS Bedrock, and other foundation-model platforms.
• Evaluate AI solutions for accuracy, relevance, latency, cost, reliability, and hallucination reduction.
• Implement appropriate guardrails, validation, observability, and human-in-the-loop mechanisms for enterprise AI applications.

Full-Stack Application Development

• Design, develop, and maintain scalable AI-powered applications using Python, FastAPI, React.js, Next.js, and Node.js.
• Develop secure and scalable REST APIs, microservices, backend services, and AI orchestration layers.
• Build intuitive web interfaces for AI-driven capabilities such as AI assistants, chatbots, search, recommendations, analytics, and workflow automation.
• Integrate AI services seamlessly into existing enterprise applications and business workflows.

Data & AI Infrastructure

• Design and implement data models and schemas using SQL Server, PostgreSQL, and NoSQL databases.
• Work with vector databases such as Pinecone, Weaviate, Milvus, Azure AI Search, or equivalent technologies.
• Build data ingestion and processing pipelines for documents, structured data, and unstructured enterprise content.
• Implement embedding generation, semantic search, metadata filtering, chunking, indexing, and retrieval strategies.
• Work with data pipeline technologies such as Apache Airflow where applicable.

Cloud & Production Engineering

• Deploy and operate AI applications on Azure and/or AWS.
• Build containerized applications using Docker and Kubernetes.
• Implement CI/CD pipelines, automated testing, monitoring, logging, and production observability.
• Design applications for security, scalability, availability, performance, and cost efficiency.
• Integrate enterprise identity, authentication, authorization, and security controls into AI applications.

Engineering & Collaboration

• Follow strong software engineering practices including Git, code reviews, automated testing, CI/CD, documentation, and Agile development.
• Collaborate with product owners, architects, data engineers, and business stakeholders to translate business requirements into AI-enabled solutions.
• Contribute to technical design decisions, architecture discussions, and engineering standards.
• Continuously evaluate emerging AI technologies and identify opportunities to apply them to real-world business problems.

Required Qualifications & Skills

• Bachelor's or Master's degree in Computer Science, Information Technology, Engineering, Artificial Intelligence, or a related discipline.
• Strong hands‑on experience with Python and modern Python frameworks.
• Strong experience building production‑grade web applications and APIs using technologies such as FastAPI, Flask, Node.js/Express, React.js, or Next.js.
• Practical experience building applications using Generative AI and LLMs.
• Hands‑on experience with Agentic AI, LLM orchestration, RAG, tool calling, and multi‑agent workflows.
• Experience with one or more AI frameworks such as LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen, or equivalent.
• Experience working with vector databases / vector search technologies and embeddings.
• Strong understanding of SQL and relational databases; experience with NoSQL databases is an advantage.
• Experience with REST APIs, microservices, asynchronous processing, and distributed application architectures.
• Experience with at least one major cloud platform, preferably Azure or AWS.
• Hands‑on experience with Docker and familiarity with Kubernetes and CI/CD practices.
• Strong understanding of Git, Agile development, testing, debugging, and software engineering best practices.
• Strong analytical, problem‑solving, communication, and collaboration skills.

Preferred / Nice-to-Have Skills

• Experience with Azure OpenAI, Azure AI Search, AWS Bedrock, Amazon SageMaker, or equivalent AI platforms.
• Experience with LLM evaluation, AI observability, prompt evaluation, and model performance monitoring.
• Experience with fine‑tuning, LoRA/PEFT, Hugging Face Transformers, or model adaptation techniques.
• Experience implementing AI security, guardrails, responsible AI, and enterprise data protection.
• Experience with MLOps / LLMOps practices.
• Contributions to open‑source AI projects, technical communities, or personal AI/Agentic AI projects.
• Experience taking an AI prototype from POC MVP production.
• Exposure to enterprise domains such as finance, telecom, manufacturing, healthcare, or supply chain is an advantage.

What Success Looks Like

In this role, you will be expected to:

• Build AI solutions that move beyond POCs into reliable production applications.
• Develop reusable AI agents, RAG components, tools, and orchestration patterns.
• Deliver high‑quality full‑stack features across the AI, backend, data, and frontend layers.
• Improve AI application accuracy, performance, reliability, and cost efficiency.
• Help establish and evolve AI‑first engineering practices across the development team.