Role: Gen AI Engineer (Backend)
Location: Remote in USA
Duration: W2 Contract (Candidate need to work on our W2)
We are seeking a Gen AI Engineer (Backend) with strong expertise in spec-based AI solution development and proven experience in taking Gen AI solutions to production. The role focuses on building scalable backend services leveraging RAG, Agentic AI, and cloud-native architectures.
👉 Backend-focused Gen AI Engineer with strong Node.js expertise, capable of building and deploying RAG/Agentic AI solutions on AWS.
Key Responsibilities
- Design and develop backend-driven Gen AI applications based on defined specifications
- Build and deploy production-grade AI solutions
- Implement RAG (Retrieval Augmented Generation) pipelines
- Develop and orchestrate Agentic AI workflows / AI agents
- Build and manage APIs for AI integrations (REST-based)
- Integrate Gen AI models (OpenAI / Azure OpenAI / similar) into backend services
- Ensure scalability, performance, and reliability of AI solutions
- Collaborate with cross-functional teams (product, frontend, architecture)
Required Skills
✅ Gen AI (Core)
- Strong hands-on experience with Gen AI / LLM-based application development
- Experience with:
- RAG implementations
- Agentic AI / multi-step AI workflows
- Experience deploying AI solutions from POC to Production
✅ Backend Development
- Strong expertise in:
- Node.js / Express.js
- Experience building scalable APIs / microservices
- System design and backend architecture concepts
✅ Cloud & Integration
- AWS (mandatory)
- Experience integrating AI/ML APIs
- Database exposure (NoSQL / SQL preferred)
Good to Have
- Exposure to tools like LangChain / LangGraph
- Experience with vector databases (Pinecone, FAISS, etc.)
- Knowledge of event-driven or serverless architectures
Thank you
Praveen
[email protected]