AI Full Stack Engineer

Atlassian Intelligence; Pune District; Hybrid; INR 900,000 - 1,400,000; Full time

Job summary

Atlassian Intelligence in Pune is seeking an AI Full Stack Engineer to own the full lifecycle of GenAI-powered products, from model & MRP integration to production-grade full stack delivery. You will design end-to-end architectures, build RAG pipelines, and develop React front-ends with Node.js/Python back ends.

Hybrid on-site work is supported. Ideal candidates have 3–5 years of experience in software/full-stack development and strong Python/React skills, with experience in AWS and Atlassian

Qualifications

• 3–5 years in software / full-stack development.
• Proficiency in Python.

Responsibilities

• Design and build end-to-end architecture for AI powered applications, from UI through backend to cloud infrastructure.
• Develop RAG pipelines, integrate LLMs, and build MCP based agentic workflows.
• Build responsive, production-quality front-end interfaces using React.
• Develop and maintain backend services and APIs using Node.js and Python.
• Deploy, scale, and monitor AI workloads on AWS. — Evaluate and monitor LLM/RAG output quality in production.
• Partner closely with product, design, and QA to translate requirements into shipped features.
• Troubleshoot independently and propose solutions — not just surface problems.

Skills

Python

React

JavaScript/TypeScript

HTML

CSS

Node.js

RESTful API design

SQL/NoSQL databases

Git

Tools

Jira

Confluence

JSM

LangChain

MCP

FAISS

ChromaDB

Pinecone

Docker

GitHub Actions

Forge or Connect

Job description

AI Full Stack Engineer

Own the full lifecycle of GenAI-powered products — from model & RAG integration to production-grade full stack delivery.

• Experience: Mid-level · 3–5 years
• Function: Engineering — AI / Full Stack
• Employment: Full-time · On-site / Hybrid

We're building GenAI-powered applications that combine large language models, retrieval systems, and cloud-native infrastructure. We're looking for an engineer who can own the full lifecycle — from model and RAG integration through to production-grade full-stack development — and ship independently with minimal oversight.

What You'll Do

• Design and build end-to-end architecture for AI powered applications, from UI through backend to cloud infrastructure.
• Develop RAG pipelines, integrate LLMs, and build MCP based agentic workflows.
• Build responsive, production-quality front-end interfaces using React.
• Develop and maintain backend services and APIs using Node.js and Python.
• Deploy, scale, and monitor AI workloads on AWS. — Evaluate and monitor LLM/RAG output quality in production.
• Partner closely with product, design, and QA to translate requirements into shipped features.
• Troubleshoot independently and propose solutions — not just surface problems.

Must-Have Skills

• 3–5 years in software / full-stack development.
• Proficiency in Python.

Core Experience

• Proficiency in React, JavaScript/TypeScript, HTML, and CSS.
• Backend development with Node.js and RESTful API design.
• SQL/NoSQL databases, Git, and version control (GitHub or Bitbucket).

AI & NLP

Strong NLP foundation: tokenization, preprocessing, POS tagging, NER, vectorization (BoW, TF-IDF, Word2Vec/embeddings).

• Solid grasp of transformer architecture (self-attention, multi-head attention, positional encoding) and how LLMs are trained.
• Hands-on experience building RAG systems, including hybrid search.
• Prompt engineering — designing, testing, and iterating on prompts for production.
• Vector databases (FAISS, ChromaDB, or Pinecone).
• Working knowledge of LangChain and MCP (Model Context Protocol).

Cloud — AWS / Atlassian

• Practical experience with core AWS services: Lambda, Bedrock, DynamoDB, and IAM.
• Hands-on experience with the Atlassian platform (Jira / Confluence / JSM).
• Experience integrating with Atlassian REST APIs and app development (Forge or Connect).

Soft Skills

• Excellent written and verbal communication skills.
• Ability to work independently and drive problems to resolution.

Good to Have

LangGraph, CrewAI, AutoGen, or similar frameworks for stateful, multi-agent applications.

• LLM/RAG evaluation and observability tooling (e.g., RAGAS, LangSmith).
• Fine-tuning experience (LoRA/QLoRA, quantization) on open models such as Gemma.
• Atlassian Forge platform (UI Kit / Custom UI, resolvers, manifest.yml, Forge Storage/SQL).
• Jira / Confluence / JSM REST APIs and OAuth 2.0 app scopes.
• SageMaker, EC2, Cognito, or S3.
• Containerization and CI/CD (Docker, GitHub Actions, or equivalent).
• API security — rate limiting, input validation, prompt-injection mitigation for LLM-facing endpoints.
• Unit testing experience (Jest or equivalent).