Full Stack AI Engineer Intern

About DigiPlusIT

At DigiPlusIT, we're not just building software; we're engineering the future. We are a dynamic software solutions provider committed to leveraging cutting-edge technology to solve complex business problems. Our focus on AI, cloud, and next-generation web applications puts us at the forefront of innovation, and we're looking for passionate minds to join us on this journey.

The opportunity: Built what's next in AI

Are you passionate about the future of AI and ready to build more than just side projects? We are hiring an ambitious
Full Stack AI Engineer Intern
to join our team.

This is a unique opportunity to move beyond theory and get hands-on experience shipping production-grade applications powered by Large Language Models (LLMs). You won't be fetching coffee; you'll be writing code that matters, building real features that integrate sophisticated AI pipelines, and working directly on our core infrastructure. You will be mentored by senior engineers and gain invaluable experience in the rapidly evolving world of Generative AI.

Responsibilities

• Build & Ship Features:
  Design, build, and maintain full-stack features in
  React,
  Node
  and
  
  (including UI, server components, and protected API routes) that integrate complex LLM and retrieval systems.
• Implement RAG Pipelines:
  Develop and own entire Retrieval-Augmented Generation (RAG) pipelines: from text ingestion, chunking, and embedding to vector storage, retrieval, and response synthesis.
• Orchestrate AI Workflows:
  Utilize frameworks like
  LangGraph
  ,
  LangChain
  or
  LlamaIndex
  to orchestrate sophisticated retrieval flows, tool usage, and multi-agent systems.
• Optimize Database Performance:
  Design and optimize data models and queries in
  MongoDB
  to ensure low latency and support high concurrency.
• Implement Caching Strategies:
  Integrate and manage caching layers using
  Redis
  (or equivalent) for embeddings, search results, and critical session data to enhance performance.
• Focus on Performance & Cost:
  Work on improving the observability, performance (latency, batching), and cost-efficiency of our AI services through prompt engineering and infrastructure tweaks.
• Collaborate on System Design:
  Contribute to system design discussions for scaling our applications, suggesting improvements for load-balancing, horizontal scaling, and fault tolerance.
• Uphold Engineering Excellence:
  Write clean, maintainable code, comprehensive tests, and clear documentation. You will also set up reproducible local/dev environments and present demos of your work.

Required Qualifications

• Strong hands-on experience building production-level applications with
  React,
  
  and
  
  .
• Practical experience integrating with the
  OpenAI API
  (specifically embeddings and chat/completions models like the gpt-* family).
• Solid understanding of Retrieval-Augmented Generation (RAG) concepts (chunking, embedding, retrieval, context windowing, answer synthesis).
• Familiarity with vector databases and retrieval systems (e.g., Pinecone, Weaviate, Milvus, Supabase Vector, or Redis with vector search).
• Experience using or a strong willingness to immediately learn
  LangGraph
  ,
  LangChain
  or
  LlamaIndex
  .
• Good practical knowledge of
  MongoDB
  , including writing optimized queries and managing indexes.
• Proficiency in modern TypeScript and a strong ability to reason about asynchronous flows and performance.
• Excellent communication skills with the ability to articulate technical tradeoffs in design notes, PR descriptions, and team discussions.
• Strong hold over rapid application development using AI-assisted coding.

Strongly Preferred

• Experience with fine-tuning techniques for LLMs (e.g., LoRA, QLoRA).
• Knowledge of multi-agent orchestration patterns (e.g., chaining, agent supervision).
• DevOps/Infrastructure experience: Docker, Kubernetes, CI/CD pipelines, and observability tools (Prometheus/Grafana).
• A keen sense for frontend UX/UI design and building accessible, responsive interfaces.
• Familiarity with cost optimization strategies for LLM usage in production.
• Proficiency in leveraging AI-powered coding assistants (e.g., GitHub Copilot) to accelerate development.
• Understanding of security and compliance considerations for handling sensitive data (PII, data retention, encryption).