Junior AI Engineer – Build LLM-powered Applications

About the role

As a Junior AI Engineer with 1–2 years of experience, you will help design, develop, and deploy AI‑driven solutions that leverage large language models, retrieval‑augmented generation and related technologies.

Key responsibilities

• Build AI‑powered applications using LLMs, RAG and Model Context Protocol.
• Implement function calling, agent orchestration and tool integration.
• Benchmark models with LLM‑as‑a‑Judge, few‑shot evaluation and automated testing pipelines.
• Containerize and deploy services with Docker and Docker Compose.
• Work with Hugging Face Transformers for embeddings, tokenization and text classification.

Required profile

• 1–2 years of hands‑on AI/ML engineering experience.
• Strong proficiency in Python.
• Familiarity with PyTorch or TensorFlow.
• Good understanding of core ML/NLP concepts, including LLMs and RAG workflows.
• Experience in Unix/Linux environments and asynchronous frameworks such as FastAPI or asyncio.
• Comfort with Docker, containerised environments and Git version control.

Required skills

• Python
• PyTorch
• TensorFlow
• FastAPI
• Docker & Docker Compose
• Git
• Hugging Face Transformers
• OpenCV
• Vector databases (e.g., Qdrant, ChromaDB)
• Relational databases (MariaDB, PostgreSQL)
• Message queues (RabbitMQ, Redis Queue)
• Agent orchestration tools (LangChain, LlamaIndex, Haystack)