Principal AI Engineer

Overview

Develop and deploy enterprise-grade generative AI solutions for the AI Enablement Team. The role focuses on autonomous agent workflows, cloud LLM integration, secure APIs, and production LLM applications.

What you'll do

• Design and deploy autonomous multi-agent workflows with orchestration frameworks.
• Build graph-based agent workflows with complex routing, parallel execution, and error recovery.
• Develop reusable agent libraries, platform patterns, versioning strategies, and testing frameworks.
• Build FastAPI applications integrating PostgreSQL, Redis, and enterprise services.
• Implement streaming interfaces using SSE and WebSockets alongside REST and event-driven APIs.
• Integrate cloud LLM providers, prompt management systems, observability, and evaluation frameworks.
• Mentor junior engineers and participate in architecture reviews and knowledge sharing.

What you'll need

• 9+ years of software engineering experience.
• 2+ years building and deploying production LLM-powered applications.
• Bachelor's or Master's degree in Computer Science, AI/ML, Engineering, Data Science, or a related discipline.
• Expert-level asynchronous Python programming and production FastAPI experience.
• Experience with agentic orchestration, multi-step autonomous agents, state management, and tool calling.
• Experience with cloud LLM providers, Docker, Git, CI/CD, and AWS, Azure, or Google Cloud.
• Experience with MCP, agent-to-agent communication, LLMOps, observability, and prompt engineering at scale.

Nice to have

• Experience in global life sciences, especially the GPS functional area.
• Experience managing or collaborating with offshore technical development teams and international stakeholders.

Details

• Location: Hyderabad, Telangana, India.