AI Engineering Intern – Agentic Systems & Rapid Prototyping

Red6.ai is an applied AI team building real systems for US businesses. We work across agentic AI, automation, documents, voice, internal tools, integrations, data workflows, and whatever new technology is needed to solve the problem in front of us.

We're looking for an AI Engineering Intern who enjoys building, experimenting, and moving fast across different problem spaces.

This is not a role focused on one specific domain or technology. One week you might be working on an AI agent that operates across multiple tools, another week experimenting with a new model or agent framework, and the next building a document pipeline, voice workflow, browser automation, data-processing system, or an entirely new prototype.

The core expectation is simple: you should be able to quickly understand a new problem, research unfamiliar technologies, build a working prototype, evaluate whether it works, and iterate rapidly.

You should already have hands-on experience building practical AI/LLM applications, preferably including agentic systems that can use tools, APIs, workflows, or external systems to complete tasks.

WHAT YOU'LL WORK ON

You'll experiment with new AI models, frameworks, tools, APIs, and emerging technologies to understand what is useful and how quickly we can turn them into working systems.

You'll build and prototype agentic workflows where models need to reason, use tools, interact with APIs or applications, manage multi-step tasks, and recover from failures.

Depending on the project, you may work on:

• AI agents and multi-step agentic workflows

• LLM applications and model experimentation

• Browser and computer automation

• Document processing, OCR, classification, and structured extraction

• Voice agents, speech-to-text, text-to-speech, and real-time workflows

• APIs, integrations, internal tools, and workflow automation

• Retrieval, search, data pipelines, and contextual systems

• Evaluations, observability, tracing, and reliability

• New AI models, frameworks, SDKs, and emerging tooling

The specific technology is less important than your ability to jump into unfamiliar areas quickly and make progress.

A significant part of the role will involve rapid experimentation. You may be given a problem where neither you nor the team initially knows the best solution. You'll be expected to research available approaches, test multiple options, build quick prototypes, compare results, and determine what should be taken forward.

We want someone comfortable moving quickly from research → prototype → evaluation → iteration → working system.

WHAT WE'RE LOOKING FOR

Strong Python fundamentals and at least one meaningful project that you built yourself. Personal projects, hackathons, freelance work, startups, and open-source contributions all count. Show us what you built and be clear about the parts you owned.

Hands-on experience building AI/LLM applications. You should have gone beyond simply calling an LLM API and have built systems involving tools, APIs, workflows, retrieval, automation, agents, or other application logic.

Experience building and deploying agentic systems is strongly preferred. We're especially interested in projects where an AI system had to take actions, interact with external systems, execute multiple steps, or make decisions based on intermediate results.

You should be comfortable picking up technologies you haven't worked with before. We don't expect you to already know every framework we use — many of the tools you'll work with may change during your internship.

What matters most is your ability to research quickly, experiment intelligently, prototype fast, and learn independently.

When you get stuck, we expect you to read documentation, inspect examples, debug the problem, experiment with alternatives, and come back with what you've learned rather than waiting for step-by-step instructions.

Familiarity with agent frameworks, LLM APIs, FastAPI, browser automation, OCR, voice APIs, vector databases, observability tools, or cloud platforms is useful, but we care much more about your ability to learn and build than about a specific technology stack.

Clear written and spoken communication is important. You'll provide regular progress updates and may participate in selected discussions with US clients.

HOW YOU'LL WORK

You'll typically be given a problem or outcome rather than a detailed implementation plan.

Your job will be to understand the problem, research possible approaches, experiment with the most promising ones, build a prototype, evaluate the results, and iterate toward a working solution.

Senior engineers will be available for direction and code review, but you should be comfortable owning your work with minimal supervision.

We value engineers who can move quickly without becoming careless — prototype fast, measure what works, discard what doesn't, and turn successful experiments into reliable systems.

As you demonstrate that you can independently explore problems and deliver working solutions, you'll take ownership of increasingly larger pieces of client and internal projects.

DETAILS

Duration: 3–6 months, full-time

Location: Remote within India

Hours: You'll need to be comfortable working some night hours in IST when collaboration with the team or US clients requires it. Other hours are flexible.

HIRING PROCESS

One technical interview and one interview with a co-founder.