We are a growing AI company delivering high-performance, asynchronous data pipeline and backend automation software to our expanding client base. We are looking for an AI Engineering Intern to help scale and optimize our backend multi-agent software networks that parse complex datasets, manage algorithmic data verification checks, and integrate securely with third-party webhooks. This is a pure backend systems engineering role focused entirely on system logic, API routing, and backend database scaling for production environments.

As an AI Engineering Intern, you will focus heavily on LLM orchestration, state machines, and building highly reliable backend infrastructures where safety, deterministic guardrails, and error-handling are critical.

What you will work on:

- Building Autonomous AI Agents: Design and implement multi-agent workflows (using frameworks like LangGraph, CrewAI, or similar state architectures) capable of self-correction and dynamic routing.
- Backend API Development: Build high-performance, asynchronous backend APIs using Python and FastAPI.
- Third-Party Integrations & Webhooks: Securely connect our core platform with major external communication platforms, database systems, and ecosystem webhooks.
- State & Data Management: Design SQL schemas to track agent execution histories and state transitions, ensuring persistence across asynchronous background loops.
- Prompt Engineering & Guardrails: Develop, test, and optimize system prompts and structured JSON outputs to guarantee agents operate safely, reliably, and within strict predefined logic constraints.

What we are looking for

- Background:



Pre-final or final year B.Tech / M.Tech / MCA students in Computer Science, Data Science, or a related technical field (or equivalent self-taught production experience).
- Core Language: Strong foundational proficiency in Python (deep understanding of async/await paradigms is required).
- AI Ecosystems: Hands-on experience building projects with open-source LLM frameworks like LangGraph, CrewAI, or LangChain, and handling direct API integrations with OpenAI or Anthropic.
- Data Validation: Robust understanding of data validation, schemas, and enforcing structured JSON outputs from LLMs using Pydantic.
- Data & APIs: Solid understanding of relational databases (SQL/PostgreSQL) and RESTful API architecture.
- Mindset: An entrepreneurial, systems-thinking attitude. You must enjoy solving complex background logic, data flow synchronization, and edge-case errors over building front-end user interfaces.

Perks & Benefits:
- Certificate of completion and Letter of Recommendation (LOR).
- Potential for a Full-Time Equivalent (FTE) role based on internship performance.
- 100% remote and flexible working environment.

To be considered for this role, you MUST attach a brief note or cover message answering the following prompt when clicking apply:

"Please describe a project where you used Python alongside an LLM framework (like LangGraph) or a complex API. If you have experience with asynchronous programming (async/await) or data validation with Pydantic, briefly explain how you structured your data flow. Please include a link to your GitHub repository if available."

(Applications using generic or automated AI-generated cover letters will be instantly archived).

📌 AI Engineering Intern (Python / LangGraph) – Remote (India)
🏢 Raysoft.ai
📍 India