AI Full StackEngineer 

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 

CORE EXPERI EN CE 

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

FU LL STACK DEVELOPM ENT 

• 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 

StrongNLP 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)

CLOU D — AWS / ATLASSI AN 

• 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 SKI LLS 

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

Good to Have

 LangGraph, CrewAI, AutoGen, or similarframeworks 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).