Software Engineer Intern

Meril is looking for a motivated SDE Intern with strong programming skills in Python or C++ and hands-on experience with LLMs, AI agents, and backend development. The candidate will work on real-world engineering problems involving AI applications, model deployment, automation, and scalable backend systems.

What you'll do

• Develop and maintain backend services using Python or C++
• Build AI agents and LLM-based workflows using LangChain, LangGraph, or similar frameworks
• Develop RAG pipelines, embeddings, and integrations with vector databases
• Deploy and serve AI/ML models through APIs
• Build and manage automated workflows using Apache Airflow
• Work with Docker, Linux, Git, and CI/CD pipelines
• Integrate APIs, databases, and AI tools into existing systems
• Debug issues, optimize performance, and write clean, maintainable code

What they ask for

• Proficiency in Python or C++
• Strong understanding of Data Structures and Algorithms, OOP, and core computer science fundamentals
• Hands on experience with projects involving LLMs, AI agents, or RAG
• Familiarity with LangChain, LangGraph, or similar AI frameworks
• Basic knowledge of SQL, databases, APIs, and Linux environments
• Understanding of Git, Docker, and model deployment
• B.Tech or M.Tech students or recent graduates in Computer Science, Information Technology, or a related field

Good to have

• Experience with vLLM, Hugging Face, or model-serving frameworks
• Familiarity with FAISS, Qdrant, Chroma, or other vector databases
• Knowledge of Apache Airflow and workflow orchestration
• Understanding of GPU-based inference and optimization
• Previous internships, open-source contributions, or relevant personal projects

Tap what's true for you. Your answers are saved for every other job too.

Put these words in your resume and practise these questions before the interview.

Technical

1. How do you implement a RAG pipeline using LangChain and vector databases?
2. What are the key differences between Python and C++ when designing high-performance backend services?
3. How do you handle model deployment and serving through APIs using Docker?

Scenario

1. What would you do if an LLM-based workflow started returning high latency or incorrect embeddings in production?
2. How would you approach debugging a memory leak in a backend service built in Python or C++?

HR

1. Why are you interested in working on AI and backend engineering at Meril?
2. Can you describe a challenging project involving LLMs or AI agents that you built during your studies or internship?

About Meril

1. How do you think Meril leverages medical device technology alongside modern AI and backend systems?

Practice questions written from the job listing, not this company's real interview questions.

Applied here? Tell the next person what happened. It's anonymous and takes one tap.