Job Description
Own the full lifecycle of GenAI-powered products — from model & RAG integration to production-grade full-stack delivery.
n
n
Experience · 3–5 years
n
Function: Engineering-AI+Full Stack
n
n
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.
n
n
What You'll Do:
n
n
— Design and build end-to-end architecture for AI-powered applications, from UI through backend to cloud infrastructure.
n
— Develop RAG pipelines, integrate LLMs, and build MCP-based agentic workflows.
n
— Build responsive, production-quality front-end interfaces using React.
n
— Develop and maintain backend services and APIs using Node.js and Python.
n
— Deploy, scale, and monitor AI workloads on AWS.
n
— Evaluate and monitor LLM/RAG output quality in production.
n
— Partner closely with product, design, and QA to translate requirements into shipped features.
n
— Troubleshoot independently and propose solutions — not just surface problems.
n
n
Must-Have Skills:
n
n
• 3–5 years in software / full-stack development.
n
• Proficiency in Python.
n
n
Full Stack Development:
n
n
• Proficiency in React, JavaScript/TypeScript, HTML, and CSS.
n
• Backend development with Node.js and RESTful API design.
n
• SQL/NoSQL databases, Git, and version control (GitHub or Bitbucket).
n
n
AI & NLP:
n
n
• Strong NLP foundation: tokenization, preprocessing, POS tagging, NER, vectorization (BoW, TF-IDF,
Word2Vec/embeddings).
n
• Solid grasp of transformer architecture (self-attention, multi-head attention, positional encoding) and how LLMs are trained.
n
• Hands-on experience building RAG systems, including hybrid search.
n
• Prompt engineering — designing, testing, and iterating on prompts for production.
n
• Vector databases (FAISS, ChromaDB, or Pinecone).
n
• Working knowledge of LangChain and MCP (Model Context Protocol).
n
n
Cloud-AWS/Atlassian:
n
n
• Practical experience with core AWS services: Lambda, Bedrock, DynamoDB, and IAM.
n
• Hands-on experience with the Atlassian platform (Jira / Confluence
n
/ JSM).
n
• Experience integrating with Atlassian REST APIs and app development (Forge or Connect).
n
n
Soft Skills:
n
n
• Excellent written and verbal communication skills.
n
• Ability to work independently and drive problems to resolution.
n
n
Valuable to Have — a strong candidate need not check every box.
n
n
• LangGraph, CrewAI, AutoGen, or similar frameworks for stateful, multi-agent applications.
n
• LLM/RAG evaluation and observability tooling (e.g., RAGAS, LangSmith).
n
• Fine-tuning experience (LoRA/QLoRA, quantization) on open models such as Gemma.
n
• Atlassian Forge platform (UI Kit / Custom UI, resolvers, manifest.yml, Forge Storage/SQL).
n
• Jira / Confluence / JSM REST APIs and OAuth 2.0 app scopes.
n
• SageMaker, EC2, Cognito, or S3.
n
• Containerization and CI/CD (Docker, GitHub Actions, or equivalent).
n
• API security — rate limiting, input validation, prompt-injection mitigation for LLM-facing endpoints.
n
• Unit testing experience (Jest or equivalent).
📌 Senior AI Full Stack Engineer (Pune)
🏢 enreap
📍 Pune