Platform Engineer III

Job Summary

The Agentic AI Engineer III contributes to application-level design and delivery for moderately complex agentic AI systems. The role helps translate business and solution requirements into scalable multi-agent designs, orchestration patterns, APIs, services, and integrations spanning applications, enterprise data, models, tools, and cloud platforms. The engineer works with architects and engineering teams to refine technical approaches, apply engineering and evaluation standards, address non-functional requirements, and coordinate implementation activities across development, platform, data, security, and product teams. The role combines hands-on technical contribution with participation in design reviews, delivery coordination, stakeholder discussions, peer support, and improvement of reusable agentic AI components and patterns.

Key Responsibilities

• Contribute to application-level design and technical implementation for moderately complex, production-grade agentic AI solutions.
• Develop and refine multi-agent orchestration, tool-use, memory, retrieval, API, integration, and human-in-the-loop patterns in alignment with agreed reference architectures.
• Translate business requirements into technical components, interface definitions, non-functional requirements, and implementation activities with support from architects and senior stakeholders.
• Participate in architecture and code reviews, and help maintain engineering standards and technical documentation.
• Apply evaluation approaches and operational quality checks covering accuracy, safety, reliability, latency, security, privacy, observability, and cost.
• Collaborate with engineers, data engineers, platform engineers, architects, security teams, and product stakeholders to support end-to-end feasibility and delivery readiness.
• Contribute to CI/CD, testing, deployment, monitoring, issue resolution, and production-readiness activities for assigned solutions.
• Identify technical dependencies, delivery risks, and design trade-offs, and discuss possible recommendations and mitigation actions with relevant stakeholders.
• Provide technical support to less-experienced engineers through reviews, knowledge sharing, and day-to-day guidance when required.
• Develop and maintain reusable agentic AI components, accelerators, templates, and implementation guidance that improve delivery consistency.
• Assess emerging agentic AI frameworks, model capabilities, and ecosystem services, and provide inputs on their suitability for enterprise use cases.
• Contribute to solution estimation, technical proposals, implementation roadmaps, and stakeholder demonstrations.

Skill Requirements

• Strong proficiency in Python and experience with relevant AI/ML frameworks and LLM APIs.
• Practical experience with agentic frameworks such as LangGraph, Semantic Kernel, LangChain, AutoGen, or equivalent technologies.
• Good understanding of API and service design, retrieval-augmented generation, vector databases, tool integration, and workflow orchestration.
• Familiarity with cloud-native architecture, microservices, CI/CD, observability, security, and production operations across Azure, AWS, or GCP.
• Experience applying evaluation approaches and Responsible AI controls for agentic and LLM-based systems.
• Ability to contribute to design discussions, analyze technical trade-offs, support engineering teams, and communicate with business and technical stakeholders.
• Strong analytical, debugging, documentation, collaboration, and delivery-coordination skills.

Other Requirements

• Bachelor’s or master’s degree in Computer Science, Artificial Intelligence, Data Science, Machine Learning, or a related field.
• Typically 4–8 years of software or AI/ML engineering experience, including hands-on delivery of generative AI, LLM, or agentic applications.
• Experience contributing to technical design and delivery for enterprise applications or AI solutions.
• Experience supporting other engineers through implementation reviews, troubleshooting, and production-readiness activities.
• Good communication and stakeholder-management skills, with the ability to explain technical considerations, risks, and recommendations clearly.
• Customer-focused, self-driven, adaptable, and capable of delivering in a rapidly evolving technology environment.