AI Engineer Intern

About the Role

Key Responsibilities

• Design and develop AI agents using LangGraph, LangChain, and DeepAgents.
• Build agent harnesses supporting planning, tool execution, context management, and multi-step workflows.
• Implement middleware for retries, error handling, human approvals, and state management.
• Develop reusable tools, sub-agents, and agent orchestration workflows.
• Build and integrate MCP servers and clients to connect AI agents with external systems.
• Implement secure tool calling, input validation, and API/database integrations.
• Implement end-to-end tracing and monitoring for LLM and agent applications.
• Analyze execution traces, tool calls, token consumption, latency, and failures.
• Design evaluation datasets and frameworks for measuring AI agent performance.
• Implement automated regression tests and evaluate correctness, consistency, hallucinations, and task completion.
• Develop LLM-powered applications using Python, prompt engineering, structured outputs, function calling, and RAG.
• Build backend APIs and services using FastAPI or similar frameworks.
• Collaborate with engineering teams to develop and deploy real-world AI solutions.

Eligibility & Required Qualifications

• Currently pursuing in the final semester or recently completed B.E., B.Tech, M.Tech, or MCA.
• Preferred disciplines: Computer Science, Artificial Intelligence, Data Science, Information Technology, or related fields.
• Strong Python programming fundamentals.
• Understanding of object-oriented programming, asynchronous programming, REST APIs, and JSON.
• Hands-on exposure to LangGraph, DeepAgents, or comparable agent frameworks.
• Understanding of agent execution loops, middleware, tool integration, state management, and error handling.
• Understanding of MCP architecture and experience building or integrating MCP servers and tools.
• Familiarity with LLM observability, tracing, monitoring, and debugging.
• Understanding of evaluation datasets, correctness metrics, and LLM evaluation methods.
• Knowledge of prompts, embeddings, structured outputs, function calling, and RAG.
• Familiarity with Git, debugging, unit testing, and basic database concepts.
• Academic projects, open-source contributions, hackathons, or independent AI projects are advantageous.

Required Technical Skills & Tools

Preferred Qualifications

• Experience with Azure OpenAI, OpenAI APIs, Anthropic, or open-source LLMs.
• Familiarity with MLflow, LangSmith, Langfuse, or OpenTelemetry.
• Experience with Pydantic, FastAPI, PostgreSQL, MongoDB, or vector databases.
• Knowledge of Docker, cloud deployment, and CI/CD pipelines.
• Exposure to multi-agent architectures, human-in-the-loop workflows, and persistent agent memory.
• Familiarity with document intelligence, information extraction, or enterprise workflow automation.
• Experience with academic AI projects, open-source contributions, or hackathons.
• Ability to explain project architecture, implementation, and technical decisions.