Trovex is a leading provider of AI-driven solutions for sales enablement and customer engagement. We specialize in developing cutting-edge technology solutions to empower businesses to streamline operations, enhance customer experiences, and drive growth. 

Position Overview

We are seeking a motivated SDE Intern with expertise in Natural Language Processing (NLP), deep learning, and modern AI development practices to join our innovative team. The ideal candidate will have experience with RAG (Retrieval-Augmented Generation), leveraging Large Language Models (LLMs), prompt engineering, and proficiency in using libraries like Langchain, Langraph along with a strong foundation in Django. Experience with modern AI development tools and AI agent frameworks is highly valued. 

Responsibilities

• Collaborate with our AI research and development team to explore and implement advanced NLP techniques, including RAG, to enhance our AI-driven solutions. 
• Develop and experiment with novel approaches for text generation, summarization, and question answering using Large Language Models (LLMs). 
• Design and craft effective prompts for various LLM applications; optimize prompting strategies for different use cases and model behaviors. 
• Utilize NLP libraries such as Langchain and Langraph to preprocess and analyze text data, and build end-to-end pipelines for various applications within our platform. 
• Assist in the integration of NLP models and pipelines into our existing Django backend infrastructure. 
• Build and train models using HuggingFace and PyTorch libraries. 
• Write clean, maintainable RESTful APIs in Django and work on integration with React frontend for AI-powered features. 
• Leverage modern AI development tools including Claude Code, Cursor, and similar IDE agents to accelerate development workflows and improve code quality. 
• Design and implement AI agent architectures using frameworks like LangGraph, AutoGen, or similar tools; explore agentic workflows for complex problem-solving. 
• Implement and manage Model Context Protocol (MCP) integrations for seamless tool and data connectivity in AI applications. 
• Work closely with cross-functional teams to understand requirements and contribute to the development of innovative AI-powered features and functionalities. 
• Collaborate with senior team members to design and execute experiments, analyze results, and iterate on model improvements. 
• Document research findings, methodologies, code implementations, and prompt engineering approaches effectively. 

Requirements

• Enrolled in or recently completed a Bachelor's or Master's degree program in Computer Science, Artificial Intelligence, or a related field, preferably in final year. 
• Strong understanding of Natural Language Processing concepts and techniques, with hands-on experience working on NLP projects. 
• Proficiency in utilizing RAG (Retrieval-Augmented Generation) and leveraging Large Language Models (LLMs) for text generation and question-answering tasks. 
• Demonstrated experience with prompt engineering, including designing, testing, and optimizing prompts for different LLM applications and use cases.
• Experience with libraries like Langchain, Langraph, HuggingFace, and PyTorch. 
• Familiarity with modern AI development tools such as Claude Code, Cursor, or similar AI-assisted development environments.
• Exposure to or experience with AI agents and agentic frameworks (e.g., LangGraph, AutoGen, Semantic Kernel); understanding of multi-step reasoning and tool-use patterns.
• Knowledge of Model Context Protocol (MCP) or similar standards for AI tool integration and communication protocols.
• Familiarity with web development frameworks, particularly Django, for backend development. 
• Solid programming skills in Python with ability to write clean, maintainable, and well-documented code. 
• Strong problem-solving abilities and genuine passion for learning and experimenting with emerging AI technologies. 
• Excellent communication skills and ability to work collaboratively in a fast-paced team environment. 
• Ability to learn quickly and adapt to new tools, frameworks, and methodologies in the rapidly evolving AI landscape. 

Nice-to-Have Skills

• Experience with vector databases (e.g., Pinecone, Weaviate, Chroma) for RAG implementations. 
• Familiarity with model evaluation frameworks and prompt testing methodologies. 
• Understanding of AI ethics, responsible AI practices, and safety considerations in LLM applications. 
• Experience with containerization (Docker) and deployment of ML models. 
• Contributions to open-source AI projects or published research. 

Benefits

• Opportunity to work on cutting-edge AI technologies and contribute to innovative, real-world projects that impact business growth. 
• Mentorship from experienced AI professionals, ML researchers, and senior engineers. 
• Hands-on exposure to the latest AI tools, frameworks, and development practices in the industry. 
• Flexible work schedule and potential for remote work options. 
• Collaborative and inclusive work culture where your contributions are valued, recognized, and directly impact product development. 
• Access to learning resources, courses, and professional development opportunities. 
• PPO (Pre-Placement Offer) opportunity if you demonstrate exceptional performance and growth throughout the internship.

Why Join Trovex?

Immerse yourself in the exciting and rapidly evolving field of Generative AI and NLP. Contribute to groundbreaking solutions that leverage state-of-the-art AI technologies while working alongside industry experts. Be part of a team that values innovation, collaboration, and pushing the boundaries of what's possible with AI. 

Apply now to become part of the Trovex family and shape the future of AI-driven solutions!