Description

Lead the design and production of agentic AI systems, RAG pipelines, and LLM-driven backend services.

This role is on-site.

Responsibilities

• Design and build agentic AI workflows for automating security, data engineering, and observability tasks.
• Implement Retrieval-Augmented Generation (RAG) pipelines using retrieval systems and vector database-backed context retrieval.
• Develop LLM-driven applications and chatbot/integration layers, managing prompt orchestration, context, memory, and tool usage.
• Build and deploy backend services and APIs for AI inference and orchestration, integrating with data pipelines and streaming architectures.
• Optimize model and system performance (accuracy, context awareness, latency, throughput, and cost) and ensure reliable production operations.

Required Skills

• 7 - 11 years of relevant experience building production software and AI/LLM systems.
• Strong programming skills in Python and hands-on development of production-grade AI services.
• LLM Ops experience to operationalize models, pipelines, and agent workflows in real environments.
• Agentic AI and RAG architecture experience, including retrieval systems and prompt orchestration.
• Backend engineering for AI inference/orchestration APIs and deployment using containerized infrastructure.
• Proficiency in Golang.

Preferred Skills

• System design and software architecture experience for scalable AI platforms.
• Leadership experience guiding technical execution and delivery.
• Data architecture experience for high-scale data processing and pipeline integration.

Key Skills

Education

Any Graduate