Job description:
Full job description
4-6 years in Full-Stack, Cloud, or AI Engineering(Strong 1 or 2 years candidates with GenAI exposure required) GCP certification is must
Job Summary
We are looking for an AWS Full-Stack Generative AI Engineer to design, build, and deploy end-to-end GenAI applications on GCP.
You will work across frontend, backend, cloud, and AI layers, building production-ready applications powered by LLMs, RAG pipelines, and APIs, and deploying them securely and scalably on AWS.
Key Responsibilities
Generative AI (Core)
· Build GenAI applications using Amazon Bedrock (Claude, Titan, etc.)
· Design and implement RAG architectures
· Work with embeddings, vector search, and semantic retrieval
· Design prompt templates, prompt chaining, and basic evaluation
· Integrate LLMs into real business workflows
Backend & API Development
· Build scalable backend services using Python (FastAPI / Flask) or Node.js
· Develop REST APIs for AI inference and orchestration
· Integrate AI services with databases and external systems
· Handle authentication, authorization, and rate limiting
Frontend Development
· Build modern web UIs using React / Next.js
· Integrate frontend with GenAI APIs
· Create responsive, user-friendly AI experiences (chat, copilots, dashboards)
AWS & Cloud Architecture
· Design and deploy applications using:
o AWS Lambda, API Gateway, Step Functions
o S3, DynamoDB / RDS
o Amazon Bedrock
· Implement IaC using CDK / Terraform (basic to intermediate)
· Ensure security, scalability, and cost optimization
Data & Storage
· Store and manage documents for RAG pipelines
· Work with vector databases:
o OpenSearch, Aurora pgvector, FAISS, Pinecone (any one)
· Handle structured and unstructured data
DevOps & Production Readiness
· Use Docker for containerized services
· Implement basic CI/CD pipelines
· Monitor logs, metrics, and errors using CloudWatch
· Support production deployments and troubleshooting
Required Skills & Qualifications
Must-Have
· Strong experience in Python or JavaScript
· Full-stack experience (frontend + backend)
· Hands-on AWS experience
· Practical experience building GenAI applications
· Understanding of:
o LLM concepts (tokens, context, inference)
o RAG pipelines
o REST APIs
· Experience with Amazon Bedrock
· Knowledge of LangChain / LlamaIndex
· Familiarity with vector databases
· Experience with Next.js
· Exposure to MLOps / AI observability
· AWS Certifications (Associate level or above)
Tech Stack (Indicative)
· Frontend: React, Next.js, Tailwind
· Backend: Python (FastAPI), Node.js
· GenAI: Amazon Bedrock, LangChain, LlamaIndex
· Data: S3, DynamoDB, RDS
· Vector DB: OpenSearch / pgvector / FAISS
· Cloud: AWS Lambda, API Gateway
· DevOps: Docker, GitHub Actions
Job Types: Full-time, Permanent
Work Location: Pune
Work Location: In person
Pay: ₹400,000.00 - ₹800,000.00 per year
Work Location: In person