GenAI Engineer

Job Requirements*

• Design and build GenAI applications using LLMs
• Implement Retrieval-Augmented Generation (RAG) pipelines
• Develop prompt engineering strategies
• Fine-tune models using LoRA/PEFT techniques
• Manage vector databases (FAISS, Pinecone)
• Optimize performance, latency, and cost
• Ensure security and compliance
• Collaborate with cross-functional teams

Python, FastAPI, Hugging Face, LangChain, FAISS, Azure OpenAI, Docker, Kubernetes

Key Responsibilities*

• Strong Python skills
• Knowledge of Transformers and LLMs
• Experience with PyTorch/TensorFlow
• Familiarity with LangChain/LlamaIndex
• Understanding of embeddings and semantic search
• Experience with RAG pipelines

AWS / Azure / GCP (Azure OpenAI preferred)

• Docker & Kubernetes

• APIs and microservices

• Fine-tuning LLMs

• Multi-modal AI models

• ML Ops / CI-CD pipelines

• GPU optimization

• Degree in Computer Science, AI, or related field

• 6 years of AI/ML experience