Backend Developer Intern – LLMs, RAG & Scalable Systems
📍 Remote | Internship
💼 Company: Ranga Technologies
🕒 Full-Time
Are you excited about building backend systems that power AI applications? Ranga Technologies is looking for a Backend Developer Intern who’s eager to work with LLMs, RAG pipelines, and modern tools like Python and Node.js
This role is ideal for someone with a strong backend foundation, interest in AI infrastructure, ability to learn and adapt quickly and is ready to start immediately.
What You’ll Work On:
- Build and optimize backend APIs for AI-powered applications
- Integrate LLMs (OpenAI, Together AI, OSS models) and manage inference pipelines
- Work with Retrieval-Augmented Generation (RAG) architectures and vector databases
- Code in Python and Node.js, supporting multi-user, scalable backend logic
- Handle batching, retries, token limits, and latency optimization
- Collaborate with AI engineers, frontend developers, and product leads
- Contribute to caching, performance, and real-time API delivery
You’re a Great Fit If You Have:
- Proficiency in Python and/or Node.js
- Basic understanding of LLMs, embeddings, and RAG systems
- Strong problem-solving ability and a fast learning curve
- Familiarity with API development and asynchronous processing
- Good understanding of scalable backend architecture
Bonus: Experience with vector databases (e.g., Pinecone, Weaviate) or Redis
What You’ll Learn:
- Real-world implementation of LLM + RAG-based systems
- How to structure and scale backend APIs for AI tools
- Practical exposure to token handling, prompt pipelines, and semantic search
- Best practices for working in a production-grade AI development environment
📩 Apply Now
Send your CV or portfolio to 👉 info@rangatechnologies.com
Subject: Backend Developer Intern Application
Generating Apply Link...
.png)
