Solution Architect – AI and Automated Solutions

Role Summary

The Solution Architect - AI and Automated Solutions partners with enterprise customers to design and deliver intelligent solutions that automate workflows, improve knowledge access, and support new product and operational capabilities. This role owns the technical journey from discovery and architecture through prototyping, production deployment, and continuous improvement.

The position works closely with business and engineering stakeholders to translate ambiguous requirements into scalable solutions integrated with existing applications, data platforms, and collaboration tools. The role may leverage cloud AI platforms such as Amazon Bedrock or Amazon SageMaker and, where appropriate, productivity ecosystems such as Microsoft 365 Copilot.

What You Will Do

Solution Architecture and Stakeholder Collaboration

• Lead discovery sessions to identify high-value use cases for AI and automated solutions, including workflow automation, copilots, knowledge retrieval, and intelligent routing.
• Translate business objectives into technical designs covering workflows, data flows, integration points, and non-functional requirements such as latency, reliability, security, and compliance.

AI and Automated Solution Design and Implementation

• Design and implement AI Agentic solutions that can reason, plan, call tools, and execute multi-step tasks across APIs, databases, SaaS platforms, and document repositories.
• Build solution workflows using patterns such as planner-executor, supervisor-worker, and human-in-the-loop with frameworks including LangChain, LangGraph, and similar orchestration libraries such as LlamaIndex and Semantic Kernel.
• Use MCP-style protocols to standardize tool discovery and invocation, including tool schemas, validation, retries, error handling, and safe execution patterns.
• Implement retrieval-augmented generation pipelines, including ingestion, chunking, metadata design, embeddings, vector indexing, hybrid search, reranking, and retrieval orchestration.
• Apply prompt and policy design techniques, including structured prompting, guarded templates, reasoning aids, and evaluation approaches to improve quality and reduce hallucinations.

Systems Integration and Productionization

• Integrate AI and automated solutions into web and mobile apps, core enterprise systems (CRM, Support, ERP, HR, finance, ticketing, supply chain), collaboration tools, and process platforms.
• Define and implement guardrails and safety controls, including authorization, policy enforcement, content filtering, PII protection, and safe tool calls.
• Work with platform and DevOps teams to deploy using cloud native patterns (containers, serverless, microservices, CI/CD).
• Use managed AI and cloud services (e.g., Amazon Bedrock, Amazon SageMaker, and core cloud infrastructure) for orchestration, hosting, and deployment.
• Design and extend AI and automated solutions using Microsoft Copilot Studio, including low-code conversational workflows, enterprise connectors, custom actions, and integrations with business systems and Microsoft 365 experiences.
• Define and track KPIs (task success, latency, cost, user satisfaction) and use monitoring, logging, tracing, and evaluation to drive continuous improvement and ensure production readiness.

What You Will Bring

• Experience integrating with cloud AI services and model platforms such as Amazon Bedrock, Amazon SageMaker, third-party LLM providers, or self-hosted open-source models.
• Experience with Microsoft Copilot Studio for building and extending enterprise AI solutions, including custom workflows, connectors, REST/API integrations, grounding with enterprise knowledge, and MCP-enabled integrations.
• Comfortable working in Python for AI application development, orchestration, and integration use cases.
• Hands-on experience building LLM-powered applications, including prompt engineering, tool-calling, structured outputs, and multi-step conversational workflows.
• Experience designing and implementing RAG systems, including document ingestion, chunking, metadata strategies, vector stores, hybrid search, and reranking.
• Familiarity with orchestration frameworks such as LangChain, LangGraph, LlamaIndex, Semantic Kernel, or equivalent platforms.
• Proven experience as a Solution Architect, Lead Engineer, or Senior Engineer designing end-to-end enterprise solutions.
• Experience with at least one major cloud platform, ideally AWS, including networking, IAM, container orchestration, and serverless services.
• Experience instrumenting AI solutions with logging, response capture, monitoring, and feedback loops for continuous improvement.