Applied AI engineer

We are seeking an Applied AI Engineer with a strong software engineering background to join our AI initiative team, focusing on building production LLM applications and implementing cutting‑edge AI solutions. This role requires hands‑on coding expertise across full‑stack development with emphasis on LLM/RAG systems.

• Build production LLM applications using FastAPI/Spring Boot backends with React/Next.js frontends
• Implement and optimize RAG systems with vector databases (Pinecone, Weaviate, Open Search)
• Create REST/Graph
  
  QL APIs for AI services integration
• Deploy containerized AI applications on AWS (ECS/EKS, Lambda)
• Assess and evaluate AI tools, making strategic build vs. buy recommendations
• Implement caching, rate limiting, and guardrails for LLM APIs

• Python
  :
  FastAPI, Flask, Django (3+ years required)
• Strong API development and microservices architecture

• RAG Implementation
  : MUST HAVE - Production experience with RAG pipelines
• Lang Chain/Llama Index
  :
  Building AI applications and chains
• Embedding Models
  :
  OpenAI, Cohere, Sentence Transformers
• Data Science
  :
  Foundation knowledge

• Git Hub Copilot/Code Whisperer
  : AI productivity tools
• AWS Bedrock
  :
  Managed foundation models
• Prompt Engineering
  :
  Advanced prompt design and optimization
• AI Guardrails
  :
  Safety and content filtering mechanisms
• Additional:
  Lambda, ECS/EKS, API Gateway, S3, DynamoDB

• 3-5 years in software engineering
• eCommerce experience strongly preferred (product search, chatbots, personalization)
• Agile/Dev Ops practices

• eCommerce AI features: conversational commerce, semantic search, content generation
• API‑first AI microservices following best practices
• POCs demonstrating AI capabilities and ROI
• Technical documentation and implementation guide