AI Solution Architect I

Job Summary

The Solution Architect designs application-level architecture, governance, and delivery of enterprise AI solutions built using OpenAI models, APIs, tools, Cyber and agentic capabilities. Translates solution architecture into secure, scalable, observable, and maintainable applications that integrate with enterprise systems, data platforms, and business workflows. Establishes engineering standards, API and tool contracts, evaluation strategies, testing frameworks, and operational guardrails for AI-enabled applications. Provides technical leadership while creating reusable components, reference implementations, and accelerators that improve delivery speed, quality, and consistency across OpenAI solution engagements.

Key Responsibilities

• Lead application architecture for OpenAI-enabled solutions, including API design, agent and workflow orchestration, tool integration, retrieval patterns, conversation state, and enterprise system connectivity.
• Define application boundaries, service contracts, data flows, integration patterns, and non-functional requirements in alignment with the overall solution and platform architecture.
• Establish coding standards, secure development practices, testing strategies, evaluation frameworks, and release guardrails for production-grade AI applications.
• Design systematic evaluations covering response quality, groundedness, task completion, safety, latency, reliability, and business outcome measures.
• Guide the implementation of responsible AI controls, including input and output moderation, prompt-injection safeguards, human-in-the-loop checkpoints, access controls, and auditability.
• Build and maintain reusable OpenAI accelerators, agent templates, tool adapters, evaluation suites, reference architectures, and application components.
• Define observability requirements for model interactions, agent actions, tool execution, errors, latency, token consumption, cost, and application-level business outcomes.
• Maintain awareness of OpenAI platform developments and assess their applicability to customer architectures, engineering standards, and reusable delivery assets.

Skill Requirements

The following AI skills are mandatory for this role:

• Strong LLM and generative AI fundamentals, including prompt and context engineering, embeddings, RAG, vector and hybrid search, reranking, structured outputs, tool/function calling, agentic workflows, model selection, and evaluation methods.
• Hands-on experience with OpenAI or Azure OpenAI APIs and SDKs, ChatGPT Enterprise use cases, OpenAI Codex or comparable AI-assisted engineering tools, including token, latency, and cost optimization.
• Strong software engineering skills in Python and/or TypeScript, with experience building secure REST APIs, microservices, tool integrations, asynchronous workflows, and maintainable automated tests.
• Experience designing systematic evaluations and observability for groundedness, response quality, task completion, tool accuracy, safety, latency, reliability, token usage, cost, and business outcomes.
• Ability to implement Responsible AI and security controls, including content moderation, prompt-injection defenses, data privacy and PII protection, role-based access, human-in-the-loop checkpoints, auditability, and operational guardrails.

Other Requirements

• 10+ years of experience in software engineering, solution or application architecture, platform engineering, or enterprise technology delivery, with demonstrable hands-on experience delivering AI/ML or GenAI solutions.
• Proven experience designing and delivering production-grade LLM applications using OpenAI, Azure OpenAI, or comparable platforms, including RAG, agents, tool integration, and enterprise data grounding.
• Strong coding capability in Python and at least one additional enterprise language such as TypeScript, Java, or C#, together with experience in APIs, microservices, cloud-native design, automated testing, and CI/CD.
• Strong knowledge of enterprise integration patterns, security, privacy, compliance, non-functional requirements, observability, and MLOps/LLMOps practices.
• Strong client-facing communication, discovery, estimation, documentation, and technical leadership skills, with the ability to explain complex architecture decisions to business and engineering stakeholders.

Preferred Qualifications

• Master’s degree in computer science, Artificial Intelligence, Data Science, Engineering, or a related field, or relevant cloud, AI, security, architecture, or data certifications.
• Experience with Azure, AWS, or Google Cloud; enterprise data platforms; vector databases and search; API management; containers and Kubernetes; DevSecOps; and MLOps/LLMOps toolchains.
• Experience in consultative or presales solutioning, regulated-industry environments, architecture governance, and creation of reusable reference architectures, accelerators, evaluation suites, and bid-response artifacts.