InfoMagnus - Artificial Intelligence Engineer - LLM/RAG

Description :

- Build and deploy LLM-powered applications, including RAG pipelines, conversational AI, and agentic workflows

- Develop and optimize prompt engineering strategies and AI system performance

- Implement vector search & retrieval systems using Pinecone, Qdrant, Milvus

- Work with agentic coding tools (GitHub Copilot, Cursor, Claude Code) for rapid development

- Build data pipelines & ML infrastructure for AI-ready data and model lifecycle management

- Deploy scalable AI systems on AWS / Azure / GCP using containerization and IaC

- Implement observability, governance, and security best practices in AI systems

- Collaborate with architects and global teams to deliver production-grade AI solutions

Key Skills & Expertise :

- Strong proficiency in Python & AI/ML development

- Hands-on with LLM frameworks : LangChain, LlamaIndex, Semantic Kernel

- Experience with LLM APIs (OpenAI, Anthropic, Azure OpenAI)

- Knowledge of RAG architectures & vector databases

- Experience in MLOps tools (MLflow, Weights & Biases)

- Familiarity with cloud platforms & DevOps (Docker, Kubernetes, Terraform)

- Exposure to AI observability, governance, and security practices

- Experience with AI-assisted development & agentic coding workflows

Why Join InfoMagnus?

- Build production-grade AI systems for global enterprises

- Work in an AI-first engineering culture with cutting-edge tools

- Contribute to proprietary AI frameworks & accelerators

- Clear growth path from Engineer ? Architect

- Exposure to end-to-end AI lifecycle