GenAi Engineer

Role Overview

HabileLabs Pvt. Ltd. is seeking a dedicated AI Engineer with 2-4 years of experience to join our Engineering department. You will focus on developing innovative LLM-based applications, agentic systems, and optimizing RAG architectures to drive digital transformation for our global clientele.

Responsibilities

• Build and optimize Retrieval-Augmented Generation (RAG) systems.
• Develop and deploy LLM-based applications and agentic systems.
• Manage the full ML lifecycle including model training, evaluation, validation, and deployment.
• Implement prompt engineering, in-context learning, and few-shot learning techniques.
• Optimize models using quantization and small language models (SLMs).
• Design and implement multi-agent systems or agentic AI frameworks.

Requirements

• 2-4 years of professional experience in AI/ML engineering.
• Deep proficiency in Python.
• Hands-on experience with LLM architectures (7B+ parameters).
• Proficiency with Git and CI/CD pipelines.
• Knowledge of Docker and cloud platforms like AWS, Azure, or GCP.
• Understanding of relational and vector databases.

Skills

• Python
• LangChain
• PyTorch
• Hugging Face
• Vector Databases

Nice to Have

• Experience with open-source models like LLaMA, Mistral, or Phi.
• Experience with model serving platforms such as vLLM, Ray Serve, or TorchServe.
• Knowledge of AI safety and model alignment.
• Experience with multi-modal models.