Description

Design and build production-grade LLM applications, RAG pipelines, and agentic workflows using Python.

This role is on-site.

Responsibilities

• Architect end-to-end LLM-powered applications and agentic workflows.
• Implement RAG pipelines over enterprise data using embeddings and vector databases.
• Build multi-step, tool-using agents with planning, execution, and memory capabilities.
• Integrate AI systems with APIs, backend services, and cloud platforms.
• Establish evaluation, reliability, and performance strategies for accuracy, latency, and cost.

Required Skills

• 5+ years of experience building and deploying production-grade backend systems.
• Strong expertise in Python.
• Hands-on experience with LLMs, including prompt engineering and orchestration.
• Proven experience with RAG architectures, embeddings, and vector databases.
• Experience with agentic frameworks such as LangChain, LangGraph, or AutoGen.
• Strong system design skills for scaling cloud-based applications.

Preferred Skills

• Experience with AutoGen for multi-agent systems.
• Background in system design for high-scale AI infrastructure.

Key Skills

Education

Any Graduate