AI Intern

Brainwonders; Mumbai City; On-site; INR 112,000 - 279,000; Full time

Job summary

Brainwonders, India's leading career counselling organization, invites enthusiastic Psychology Interns to join a 6-month internship in Mumbai (Churchgate). The role focuses on building LLM-powered AI agents, agentic reasoning, and multi-agent coordination within an educational psychology context.

Candidates with 0–1 year experience or freshers are encouraged to apply. This internship offers exposure to AWS deployment, LangChain, and cutting-edge AI frameworks, with potential full-time conversion.

Qualifications

• Strong understanding of LLMs, tokenization, transformers, embeddings, and generative AI fundamentals.

Responsibilities

• Build and test LLM-powered applications, AI agents, and autonomous workflows.
• Design and implement agentic AI systems capable of planning, reasoning, tool use, and task execution.
• Develop multi-agent systems where multiple specialized agents collaborate to solve complex tasks.
• Experiment with agent frameworks such as LangGraph, CrewAI, LangChain, and other emerging agentic AI frameworks.
• Implement agent memory, state management, task decomposition, planning, routing, and orchestration.
• Integrate agents with external tools, APIs, databases, search systems, and other services using function/tool calling.
• Explore Model Context Protocol (MCP) and other approaches for connecting AI agents with external tools and data sources.
• Use and adapt transformer-based models such as LLaMA, Mistral, and other open-source or proprietary LLMs for domain-specific applications.
• Build RAG pipelines using embeddings and vector databases for knowledge retrieval and contextual reasoning.
• Deploy AI models, agents, and supporting services on AWS (Lambda, EC2, S3, SageMaker, etc.).
• Work on prompt engineering, structured outputs, fine-tuning, model selection, and pipeline optimization.
• Develop evaluation strategies to measure agent accuracy, reliability, latency, cost, and task completion.
• Implement monitoring, logging, and debugging for LLM and agentic workflows.
• Collaborate with the team to prototype and productionize AI copilots, autonomous workflows, and intelligent automation systems.

Skills

LLMs

Python

Pandas

NumPy

HuggingFace

LangChain

LangGraph

CrewAI

Agent concepts

Multi-agent

RAG

Vector databases

AWS basics

ML fundamentals

End-to-end AI apps

Tools

Pandas

NumPy

Hugging Face

LangChain

LangGraph

CrewAI

Job description

Brainwonders is India's leading career counselling and guidance organization, helping students make informed academic and career decisions through scientifically validated psychometric and biometric assessments. Our services are trusted by educational institutions, parents, and students across the country.

With a strong presence in schools and colleges, Brainwonders is committed to empowering students by providing career guidance, counselling, and developmental support through a team of trained psychologists and counsellors.

We are looking for enthusiastic Psychology Interns who are passionate about working with students, learning professional counselling practices, and gaining real-world exposure in educational psychology.

Job Description

Company Name : BRAINWONDERS
Experience: 0–1 Year & Freshers / 2026 Pass-outs can apply)

Location: Churchgate
Type: Internship 6 months | Possibility of Full-time

Focus Areas

• Large Language Models (LLMs)
• Agentic AI & Autonomous Systems
• Multi-Agent Systems & Agent Orchestration
• ML Fundamentals & Transformers
• RAG, Embeddings & Vector Databases
• Cloud Deployment & Scaling on AWS

Responsibilities

• Build and test LLM-powered applications, AI agents, and autonomous workflows.
• Design and implement agentic AI systems capable of planning, reasoning, tool use, and task execution.
• Develop multi-agent systems where multiple specialized agents collaborate to solve complex tasks.
• Experiment with agent frameworks such as LangGraph, CrewAI, LangChain, and other emerging agentic AI frameworks.
• Implement agent memory, state management, task decomposition, planning, routing, and orchestration.
• Integrate agents with external tools, APIs, databases, search systems, and other services using function/tool calling.
• Explore Model Context Protocol (MCP) and other approaches for connecting AI agents with external tools and data sources.
• Use and adapt transformer-based models such as LLaMA, Mistral, and other open-source or proprietary LLMs for domain-specific applications.
• Build RAG pipelines using embeddings and vector databases for knowledge retrieval and contextual reasoning.
• Deploy AI models, agents, and supporting services on AWS (Lambda, EC2, S3, SageMaker, etc.).
• Work on prompt engineering, structured outputs, fine-tuning, model selection, and pipeline optimization.
• Develop evaluation strategies to measure agent accuracy, reliability, latency, cost, and task completion.
• Implement monitoring, logging, and debugging for LLM and agentic workflows.
• Collaborate with the team to prototype and productionize AI copilots, autonomous workflows, and intelligent automation systems.

Requirements

• Strong understanding of LLMs, tokenization, transformers, embeddings, and generative AI fundamentals.
• Good Python programming skills.
• Familiarity with tools/libraries such as Pandas, NumPy, Hugging Face, LangChain, LangGraph, or CrewAI.
• Understanding of AI agent concepts, including tool calling, planning, reasoning, memory, state, and orchestration.
• Basic understanding of multi-agent architectures and how multiple agents can collaborate or delegate tasks.
• Familiarity with RAG, vector databases, semantic search, and embeddings.
• Exposure to AWS services such as EC2, Lambda, S3.
• Basic knowledge of machine learning and hands‑on project experience.
• Ability to build and debug end-to-end AI applications.
• Strong curiosity and willingness to experiment with rapidly evolving agentic AI technologies.

Good to Have

• Hands‑on experience building an AI agent or multi‑agent system.
• Experience with LangGraph, CrewAI, AutoGen, or similar agent frameworks.
• Experience implementing tool/function calling and agent–API integrations.
• Familiarity with MCP (Model Context Protocol).
• Experience with agent memory, state management, planning, routing, and workflow orchestration.
• Experience with Docker.
• Experience evaluating LLMs or agents using automated evaluation frameworks.
• Contributions to open‑source AI tools, models, agents, or frameworks.
• Personal projects involving LLMs, RAG, AI agents, or multi-agent systems.

Internship Details

Location: Churchgate
Working Days: Monday to Saturday
Working Hours: 10:00 AM – 7:00 PM
Duration: 6 Months
Stipend: 10-25k per month (Based upon skillset)