AI/ML Engineer - LLM Apps

Role Overview

We are looking for an AI/ML Engineer to build and manage scalable, reliable AI applications. You will work on modern AI systems, including LLM-based applications, and help take them from development to production.

Key Responsibilities

• Build and deploy AI/ML applications
• Develop and maintain RAG pipelines
• Work with agent-based frameworks
• Integrate AI solutions into backend systems
• Monitor and improve performance, reliability, and cost
• Troubleshoot issues in production environments

Required Skills

• Good understanding of LLMs and AI/ML concepts
• Strong Python programming skills
• Experience with RAG pipelines
• Familiarity with agent frameworks

Good to Have

• CI/CD and MLOps basics
• FastAPI, Gunicorn, and containerized deployments (Docker)
• Frameworks like LangChain or LlamaIndex
• Vector databases (Pinecone, Chroma, AWS Knowledge Base)
• AWS or other cloud platforms
• Basic observability (logs, metrics, monitoring)
• Experience with debugging AI systems and optimizing costs (ref: hirist.tech)