NOTE: Based on your performance, you will be eligible for payment after the successful completion of the three-month internship.

About the Role

Were building a high-performance chat platform and seeking an AI/GenAI Engineer to lead the integration and optimization of Large Language Models (LLMs). Youll design intelligent chat pipelines, fine-tune models for domain use cases, and collaborate with our React and Python teams to deliver real-time, high-quality AI experiences at scale.

Key Responsibilities

Integrate and optimize LLM APIs (OpenAI, Claude, Gemini, open-source models).

Design robust API wrappers, handle streaming, rate limiting, and error recovery.

Implement RAG pipelines with vector databases (Pinecone, Weaviate, Qdrant, etc.).

Develop prompt engineering, fine-tuning (LoRA/QLoRA), and domain adaptation strategies.

Optimize latency, caching, and token usage; build fallback chains for reliability.

Implement safety guardrails, moderation filters, and evaluation frameworks.





Deploy scalable infrastructure for concurrent AI interactions with monitoring and logging.

Required Skills & Experience

Hands-on experience with LLMs and GenAI (OpenAI, Claude, Gemini, etc.).

Robust in Python, especially FastAPI, LangChain, LlamaIndex.

Experience with RAG, vector databases, prompt tuning, and fine-tuning (LoRA/PEFT).

Familiar with embedding models, semantic search, and function calling/tool use.

Solid understanding of transformer models, inference frameworks (vLLM/TGI), and API integration.

Exposure to MLOps tools (W&B;, MLflow) and cloud platforms (AWS/GCP/Azure).

Tech Stack

Python, FastAPI, LangChain, LlamaIndex, OpenAI/Claude/Gemini APIs, Pinecone/Weaviate/Qdrant, Redis, Docker, PostgreSQL, AWS/GCP/Azure.

NOTE: Based on your performance, you will be eligible for payment after the successful completion of the three-month internship.

📌 AI/GenAI Engineer_Unpaid internship (Hyderabad)
🏢 Smartncode
📍 Hyderabad