Job Summary

Platform Engineer III

Job Summary

Lead the deployment and solutioning of Generative AI and agentic systems in customer environments by owning end-to-end implementation across integration, testing, and stabilization phases. Collaborate with architects, product, and platform teams to design and deliver scalable, reliable, and production-grade AI solutions, ensuring adherence to standards, governance, and performance expectations.

Key Responsibilities

• Lead end-to-end customer deployments across pilot, stabilization, and production phases
• Design and implement AI solution architectures, including APIs, workflows, integrations, and orchestration layers
• Build and optimize RAG pipelines, agent workflows, and orchestration frameworks for real-world use cases
• Define and execute testing, validation, and evaluation frameworks to ensure solution quality and performance
• Monitor system performance and proactively identify, diagnose, and resolve issues across system layers
• Work across data, APIs, and platform components to ensure scalable and resilient system integration
• Drive best practices for safety, governance, and responsible AI implementation across deployments
• Create reusable solution patterns, accelerators, and documentation to improve delivery efficiency
• Collaborate with cross-functional teams (engineering, platform, support, product) to align solution design and execution
• Lead debugging and troubleshooting efforts across production systems, ensuring timely resolution
• Mentor and guide FDE I, II, and III engineers, contributing to team capability building

Skill Requirements

• Strong expertise in Python and software engineering best practices
• Deep understanding of APIs, microservices, and distributed system integration
• Hands-on experience with cloud platforms (Azure / AWS / GCP) and deployment architectures
• Proven experience working with Generative AI / LLM-based systems in production environments
• Strong problem-solving and system-level debugging skills
• Effective communication skills, including ability to engage with customer and internal stakeholders

Other Requirements

• Experience with OpenAI / Azure OpenAI or similar APIs
• Strong knowledge of RAG architectures, prompt engineering, and evaluation frameworks
• Hands-on experience with agent frameworks (LangChain, LangGraph, AutoGen, etc.)
• Familiarity with vector databases, data pipelines, and large-scale data handling
• Experience with observability, monitoring, and performance optimization tools
• Exposure to cost, performance, and reliability optimization for AI systems