AI Engineering Intern at Tapza Technologies AI Engineer Intern Company: Tapza Technologies Industry: Healthcare Technology Location: Hyderabad, Telangana Work Mode: On-Site Employment Type: Full-Time Internship Stipend: ₹15,000 – ₹25,000 per month Experience: Freshers / Experienced Candidates About Tapza Technologies Tapza Technologies is a healthcare technology company building AI-powered software solutions for pharmacies, healthcare providers, and the broader healthcare ecosystem. We are looking for an enthusiastic and technically strong AI Engineer Intern to join our engineering team and work on real-world AI applications involving LLMs, Generative AI, AI Agents, RAG, Voice AI, OCR, and Open-Source AI Models. This is a hands-on engineering role where you will experiment with emerging AI technologies, build prototypes, solve real-world healthcare problems, and contribute to taking successful AI solutions toward production.

Key Responsibilities

- Build LLM-powered applications and AI agents for real-world healthcare use cases.
- Design and develop agentic workflows using LangGraph and related frameworks.
- Build Retrieval-Augmented Generation (RAG) systems using embeddings, vector databases, retrieval, and reranking.
- Experiment with and integrate open-source LLMs such as Llama, Qwen, Mistral, Gemma, and other emerging models.
- Develop conversational AI applications integrating Speech-to-Text (STT), LLMs, and Text-to-Speech (TTS).
- Work on AI-powered solutions for pharmacy and healthcare workflows.
- Build and optimize real-time AI systems with a focus on responsiveness, reliability, and scalability.
- Work on Real-Time AI and Low-Latency Systems, optimizing end-to-end AI pipelines.
- Explore streaming, asynchronous processing, caching, parallel execution, and efficient model inference.
- Integrate AI systems with APIs, databases, vector databases, and external healthcare tools.
- Experiment with different models, prompts, retrieval strategies, and agent architectures.
- Evaluate AI systems based on accuracy, latency, relevance, reliability, and hallucination.
- Build prototypes and contribute to converting successful AI experiments into production-ready solutions.
- Write clean, modular, maintainable, and well-tested Python code.
- Stay updated with the latest developments in Generative AI, Agentic AI, open-source models, and AI engineering.

Required

Skills





- Strong programming skills in Python.
- Good understanding of Machine Learning and Deep Learning fundamentals.
- Robust understanding or practical interest in LLMs and Generative AI.
- Familiarity with RAG, embeddings, and vector search.
- Familiarity with LangChain, LangGraph, or similar AI frameworks.
- Understanding of REST APIs and software engineering fundamentals.
- Strong problem-solving and debugging skills.
- Ability to learn new AI technologies and frameworks quickly.
- Solid interest in building practical AI applications. Nice to Have
- Hands-on experience with LangGraph and AI Agents.
- Experience building RAG applications.
- Experience with vector databases such as FAISS, Qdrant, Pinecone, Weaviate, or Milvus.
- Experience with Hugging Face Transformers.
- Experience working with Llama, Qwen, Mistral, Gemma, or other open-source LLMs.
- Exposure to STT/TTS and Voice AI systems.
- Experience with Whisper or other speech models.
- Familiarity with PyTorch.
- Exposure to vLLM, Ollama, or other LLM inference frameworks.
- Understanding of Real-Time AI and Low-Latency Systems.
- Experience with Git, Docker, or cloud platforms.
- Experience with AI/ML personal projects, GitHub contributions, hackathons, research, or open-source projects.
- Exposure to OCR, document intelligence, medical data, pharmacy systems, or healthcare applications is an added advantage. Real-Time AI &

- Low-Latency Systems You may work on real-time AI pipelines such as: User Input →
- STT →
- AI Agent / LangGraph →
- RAG / Tools →
- LLM →
- TTS →
- Real-Time Response You will explore ways to make these systems faster, more reliable, and production-ready through:
- Streaming inference
- Asynchronous processing
- Parallel execution
- Caching
- Efficient retrieval
- Model and inference optimization
- Reducing unnecessary LLM calls
- Identifying and resolving pipeline bottlenecks
- Improving end-to-end response latency Healthcare AI Applications At Tapza Technologies,



you may work on AI applications related to:
- Pharmacy management
- Medicine and product intelligence
- Prescription and medical document processing
- AI-powered OCR and document extraction
- Healthcare data processing
- Intelligent search and retrieval
- Pharmacy inventory intelligence
- Conversational AI for healthcare workflows
- Automated reports and insights
- AI-powered healthcare assistants
- Voice-enabled healthcare applications Who Should Apply? We are looking for freshers and experienced candidates who are passionate about AI and enjoy building real-world applications. You do not need to know every technology listed above.

We value candidates who demonstrate:

- Strong Python and programming fundamentals
- Practical understanding of AI/ML concepts
- Curiosity about Generative AI and emerging technologies
- Hands-on project experience
- Solid problem-solving and debugging skills
- Ability to learn quickly
- A strong builder mindset
- Willingness to experiment, test, and iterate Candidates with personal projects involving LLMs, RAG, AI Agents, Voice AI, OCR, or open-source models will be highly valued.

Educational Background

Candidates with a degree or relevant technical background in:

- Computer Science
- Artificial Intelligence
- Data Science
- Information Technology
- Electronics / Electrical Engineering
- Or a related technical field Freshers with strong practical AI/ML projects are encouraged to apply.

Core Technologies

Python

- LLMs
- LangGraph
- RAG
- AI Agents
- Open-Source LLMs
- STT
- TTS
- OCR
- Vector Databases
- APIs
- Real-Time AI
- Low-Latency Systems
- PyTorch What You Will Get
- Hands-on experience building real-world AI applications for healthcare.
- Exposure to modern Generative AI and Agentic AI technologies.
- Opportunity to work with LLMs, RAG, AI Agents, Voice AI, OCR, and real-time AI systems.
- Practical experience in AI prototyping and production engineering.
- Opportunity to work on AI products used in the pharmacy and healthcare ecosystem.
- Exposure to real-world healthcare data and workflows.
- Mentorship and experience working in a product-focused technology environment.
- Potential opportunity for a full-time position based on performance and business requirements.

Location

Hyderabad

Salary

₹15,000 – ₹25,000

Experience

Not specified

📌 AI Engineering Intern (Hyderabad)
🏢 DevHub
📍 Hyderabad