Description

You will architect and deploy production-grade AI/ML solutions, focusing on agent-driven workflows and LLM applications.

This role is on-site.

Responsibilities

• Design and implement end-to-end LLM-powered applications with supervisor/sub-agent systems.
• Build scalable APIs, asynchronous workflows, and enterprise AI integrations using Python.
• Create retrieval pipelines using vector databases, embeddings, and similarity search.
• Develop prompt engineering, context management, and structured output validation frameworks.
• Deploy cloud-native solutions on AWS with CI/CD pipelines, observability, logging, and tracing.

Required Skills

• 5+ years of experience in Python backend development and data science.
• Strong proficiency in AI/ML, Generative AI, and LLM application development.
• Experience with RAG (Retrieval-Augmented Generation) and vector databases.
• Expertise in agent-based workflow design and intelligent orchestration.
• Hands-on experience with AWS cloud-native environments.
• Knowledge of CI/CD practices and environment management.
• Ability to translate business use cases into production-grade technical solutions.

Preferred Skills

• Experience with structured output validation and post-processing frameworks.
• Background in designing complex enterprise system integrations.

Key Skills

Education

Any Gradute