Internship · Remote (India)

AI Engineering Intern

Cehpoint is hiring for this role: internship, Remote (India), ₹10,000–₹20,000/month. Build and ship real AI features with our team.

About the role

Work alongside senior AI engineers to develop, optimize, and deploy LLM-powered applications, multi-agent frameworks, and vector search pipelines for enterprise clients.

Work alongside our engineers to build LLM-powered features, agents and integrations that go live for real clients. You'll write code, test prompts, wire up APIs and see your work shipped. Great for someone hungry to learn how production AI is actually built.

What you should know

  • Python 3.10+ async programming or modern Node.js/TypeScript architecture
  • Foundations of LLMs: context windows, embeddings, prompt engineering, fine-tuning vs RAG
  • Vector databases (Postgres pgvector, Qdrant, or Pinecone) and semantic similarity search
  • REST API architecture, streaming endpoints, and asynchronous event loops

What you should be able to do

  • Clean, modular code architecture and API integration
  • Hands-on experience with OpenAI, Claude, or Gemini APIs and open weights
  • Git version control and collaborative GitHub PR workflows
  • Debugging, token profiling, and latency optimization in production AI pipelines

How you work

  • Obsessive curiosity about autonomous agents and multi-step reasoning systems
  • Eagerness to dissect new AI research papers and evaluate open-source models
  • A builder mindset focused on real business problem-solving over toy demos

Skills we check

  • Python or JavaScript
  • Curiosity about LLMs / AI
  • Basic Git
  • Problem-solving

How we select for this role

We read every application ourselves. Here is what happens after you apply.

  1. Apply with a short form

    Paste a link to your CV and answer five questions in your own words. No sign-in and no file upload. About fifteen minutes.

  2. Integrity check

    When you press Check my answers, an automated check confirms the answers were typed by you. You see the result straight away, before you submit.

  3. Choose your project date

    If no cheating is detected you are shortlisted, and we email you a link to choose the day your project starts.

  4. 5-day practical project

    On that day our team contacts you with the brief: real work, 5 working days, reviewed by an engineer. For this role: Implement and evaluate an autonomous document-grounded retrieval agent with latency under 1.5s, validated by automated test suite.

  5. Offer

    If your work solves the problem well, you receive your offer letter by email and in the portal.