WALK IN INTERVIEWS SLOTS : 03-04 Sept, 2026 (11 AM to 5 PM)
Location: Prahaladnagar, Ahmedabad, Gujarat, India
Work Mode: On-site
Internship Duration: 6 Months
Openings: 1
Role Type: Internship
Arihant AI builds AI-powered business solutions, enterprise software, ERP systems, automation platforms, and intelligent applications for organizations across different industries.
Our engineering team works at the intersection of Generative AI, Python, ERP systems, automation, and enterprise data.
As an LLM Developer (GenAI – Python) Intern, you will work on real-world AI engineering projects involving LLMs, RAG systems, local model deployment, AI-powered ERP workflows, APIs, databases, and intelligent business applications.
This is a highly hands-on role for someone who wants to go beyond simply calling an AI API and learn how production-grade GenAI systems are designed, integrated, secured, and deployed.
We are looking for a technically curious Python / GenAI Intern who wants to build practical AI systems.
You will work with senior developers and AI engineers to develop AI-powered features that connect language models with enterprise applications and business data.
Depending on your skills and project requirements, you may work with commercial LLM APIs, open-source/local models, RAG pipelines, vector databases, Odoo/ERP systems, Python backends, AI guardrails, and tool-based AI workflows.
You are not expected to know every technology listed below before joining.
Strong Python fundamentals, problem-solving ability, curiosity, and the ability to learn independently are the most important requirements.
- Build AI-powered features using commercial and open-source language models.
- Integrate LLMs into real-world business applications and workflows.
- Develop Python-based orchestration logic for LLM applications.
- Work with prompts, context management, structured outputs, tool calling, and model responses.
- Experiment with different models and approaches to improve quality, latency, reliability, and cost.
- Evaluate AI outputs and identify failure cases.
- Build and improve Retrieval-Augmented Generation (RAG) pipelines.
- Work with documents, structured data, and other enterprise knowledge sources.
- Implement document processing, chunking, embeddings, retrieval, and context construction.
- Work with vector databases such as FAISS, ChromaDB, Qdrant, or Pinecone.
- Evaluate retrieval quality and improve the relevance of generated responses.
- Build AI systems that can answer questions using private enterprise data.
- Experiment with locally hosted open-source language models.
- Learn and work with tools such as Ollama, Hugging Face, or vLLM.
- Understand the basics of model inference, quantization, resource requirements, and latency.
- Compare local models with commercial APIs for different use cases.
- Help build privacy-focused AI solutions where sensitive enterprise data should remain within controlled environments.
- Develop clean, maintainable Python code.
- Build backend services and APIs supporting AI-powered applications.
- Work with databases and structured enterprise data.
- Debug, test, and optimize AI and backend workflows.
- Read and improve existing codebases.
- Write reusable components instead of building one-off scripts.
- Integrate AI capabilities into Odoo and enterprise workflows.
- Work with Python-based Odoo modules and the Odoo ORM.
- Understand how AI systems interact with business models and relational databases.
- Work with PostgreSQL and enterprise data structures.
- Develop AI-powered utilities, assistants, and workflow automation inside ERP applications.
- Implement input and output validation for AI systems.
- Develop guardrails to reduce unsafe, irrelevant, or unauthorized model behavior.
- Explore rule-based and model-based validation approaches.
- Test AI systems against unexpected, adversarial, or problematic inputs.
- Help protect sensitive enterprise information from unintended exposure.
- Monitor AI workflows for reliability and consistency.
- Strong understanding of Python fundamentals.
- Good understanding of Object-Oriented Programming.
- Strong problem-solving and debugging ability.
- Understanding of functions, modules, classes, exceptions, data structures, and APIs.
- Basic understanding of SQL and relational databases.
- Understanding of JSON and HTTP/API concepts.
- Ability to read technical documentation and learn independently.
- Good communication and teamwork skills.
- Genuine interest and understadning in Generative AI and modern AI technologies.
Experience or familiarity with any of the following will be an advantage:
-
OpenAI, Anthropic, Gemini, or other LLM APIs
- Hugging Face
- Ollama
- vLLM
- LangChain or similar frameworks
- RAG architecture
- Embeddings and vector search
- FAISS, ChromaDB, Qdrant, or Pinecone
- Odoo development
- Odoo ORM
- PostgreSQL
- REST APIs
- Docker
- Linux
- Git/GitHub
- Prompt engineering
- AI agents and tool calling
- LLM evaluation
- AI guardrails
- Model quantization
- Local LLM deployment
You do not need to know all of these technologies. Strong Python fundamentals and the ability to learn quickly are more important.
You may be a good fit if you:
-
Enjoy understanding how AI systems actually work.
- Like experimenting with new models, tools, and approaches.
- Can go through documentation, GitHub repositories, and technical articles to solve problems.
- Are comfortable debugging when things don't work as expected.
- Prefer understanding the underlying technology instead of blindly depending on frameworks.
- Are interested in both AI and backend/software engineering.
- Can work independently while knowing when to ask for help.
- Care about security, privacy, reliability, and correctness.
- Are excited about applying AI to real business problems.
We are looking for engineers in the making—not just candidates who have experimented with ChatGPT.
During the 6-month internship, you will gain practical experience in:
-
Large Language Model application development
- LLM API integration
- Open-source and local LLM deployment
- Prompt and context engineering
- RAG architecture
- Embeddings and vector databases
- AI agents and tool calling
- LLM evaluation and reliability
- AI guardrails and security
- Python backend development
- REST APIs
- PostgreSQL and enterprise data
- Odoo/ERP integration
- AI-powered business automation
- Git-based software development
- Debugging and production-oriented engineering
- Hands-on experience with real-world GenAI projects.
- Exposure to enterprise AI rather than only experimental/demo applications.
- Mentorship from experienced AI and software engineers.
- Opportunity to work with both commercial and open-source AI models.
- Experience building AI systems around private enterprise data.
- Exposure to ERP, business automation, and intelligent workflow systems.
- Opportunity to understand how AI applications move from prototype to production.
- Internship completion certificate.
- Letter of Recommendation based on performance.
- Potential full-time opportunity based on performance and business requirements.
- Duration: 6 months
- Location: Ahmedabad, Gujarat, India
- Work Mode: On-site
- Openings: 1
- Experience: Freshers and students/recent graduates with strong technical fundamentals are welcome to apply.
- Start Date: As mutually agreed.
- Stipend: To be discussed based on skills and interview performance.
If you are excited about Generative AI, Python, and building intelligent software that solves real business problems, we'd love to hear from you.
Apply now and start your journey toward becoming a production-focused GenAI engineer.
