Senior Lead, Support

Role Summary The AI Business Solutions Engineer is a hands-on technical problem solver who translates business problems into intelligent, AI-enabled solutions. This person works directly with business and operations teams to understand broken workflows, identify friction, map system and data dependencies, and rapidly build practical solutions using AI agents, MCP servers, APIs, automation tools, RAG, data pipelines, and modern AI platforms. This is not a traditional business analyst, transformation strategist, or prompt-only AI role. This is an individual contributor role for someone who can design, build, connect, test, document, and deploy solutions. The ideal candidate combines business maturity with strong technical execution and can move quickly from discovery to prototype to scalable implementation. Key Responsibilities Translate ambiguous business problems into clear technical requirements, process maps, solution designs, data needs, integration plans, and measurable outcomes. Design, build, test, and deploy agentic workflows that retrieve information, reason over business context, summarize insights, trigger actions, route work, escalate exceptions, and support human-in-the-loop decisions. Create, deploy, troubleshoot, and connect MCP servers that allow AI systems to securely access enterprise tools, data, workflows, APIs, prompts, and resources. Build or connect MCP servers for systems such as Salesforce, ServiceNow, Jira, Confluence, Snowflake, Databricks, Power BI, LMS/CMS platforms, customer data platforms, knowledge repositories, internal applications, and external APIs. Integrate enterprise systems through REST APIs, GraphQL, webhooks, SDKs, middleware, iPaaS tools, event-driven workflows, and custom connectors. Build AI-enabled applications, assistants, automations, and internal tools using modern AI platforms, LLM APIs, agent frameworks, workflow tools, and integration services. Implement RAG and enterprise search patterns using embeddings, vector databases, document ingestion, chunking strategies, metadata filtering, retrieval evaluation, and permission-aware access. Build solutions for use cases such as case triage, account intelligence, support operations, knowledge retrieval, reporting automation, workflow routing, operational summarization, and executive decision support. Implement guardrails, approval gates, authentication patterns, access controls, logging, observability, fallback logic, and exception handling for AI-assisted workflows. Partner with business, IT, data, security, and operations teams to ensure solutions are practical, secure, governed, documented, supportable, and aligned to measurable business outcomes. Required Skills & Experience 5+ years of experience in software engineering, solutions engineering, automation engineering, enterprise systems integration, data engineering, AI engineering, technical business operations, or related technical roles. 2+ years of hands-on experience building AI-enabled solutions, automation workflows, intelligent assistants, RAG systems, LLM applications, AI agents, or agentic workflows. Demonstrated ability to translate business problems into working technical solutions, not just strategy recommendations or requirements documents. Hands-on experience designing, creating, deploying, troubleshooting, or integrating MCP servers or similar tool/context integration layers for AI systems. Ability to connect multiple tools, data sources, systems, or MCP servers into coordinated workflows that allow AI systems to retrieve context and perform governed actions. Strong working knowledge of AI agent patterns, tool calling, function calling, RAG, vector search, prompt engineering, context engineering, orchestration, guardrails, and human-in-the-loop design. Experience building or integrating APIs, enterprise systems, data sources, workflow automation tools, or internal business applications. Experience with at least one modern programming language such as Python, TypeScript, JavaScript, C#, Java, or Go. Experience with Git, JSON schemas, SDKs, debugging, logging, testing, documentation, deployment pipelines, and basic cloud or infrastructure concepts. Experience with enterprise systems such as Salesforce, ServiceNow, Jira, Confluence, Power BI, Snowflake, Databricks, LMS/CMS platforms, customer data platforms, knowledge management systems, or similar tools. Strong communication skills with the ability to explain AI architecture, integration patterns, technical tradeoffs, and solution design in clear business language. Technical Qualifications The ideal candidate should have hands-on experience with several of the following: AI platforms and agent frameworks: OpenAI APIs/Agents SDK, Anthropic Claude, Amazon Bedrock Agents, Azure AI Foundry, Google Vertex AI Agent Builder, LangGraph, LangChain, LlamaIndex, CrewAI, AutoGen, Semantic Kernel, or comparable platforms. MCP, APIs and integration: MCP server creation, configuration, debugging, deployment, tool/resource definitions, authentication, permissions, logging, REST APIs, GraphQL, webhooks, SDKs, JSON/YAML, OAuth, service accounts, and secure connector design. RAG, data and knowledge systems: Embeddings, vector databases, metadata filtering, document ingestion, retrieval evaluation, SQL, data modeling, BI/reporting tools, enterprise search, permission-aware retrieval, and knowledge management patterns. Engineering and deployment: Python, TypeScript/JavaScript, Node.js, FastAPI, Flask, Express, GitHub/GitLab, CI/CD, Docker, cloud deployment, logging, tracing, monitoring, evaluation, and cost tracking. Automation and workflow tools: Workato, Zapier, Make, n8n, Power Automate, ServiceNow Flow Designer, MuleSoft, Boomi, event-driven automation, approval workflows, routing logic, SLA triggers, and operational playbooks. Preferred Qualifications Experience building production-grade AI agents, MCP servers, RAG applications, AI-powered internal tools, or enterprise automation workflows. Experience integrating AI with customer operations, support operations, revenue operations, IT operations, marketing operations, finance operations, or HR operations. Familiarity with enterprise security, compliance, data privacy, responsible AI, governance, audit trails, and access-control design. Experience deploying AI solutions in AWS, Azure, Google Cloud, or comparable cloud environments. Ability to evaluate AI tools and platforms and recommend the right architecture based on business value, speed, risk, cost, and scalability. Success Measures Success in this role will be measured by the ability to: Translate complex business problems into working AI-enabled technical solutions. Build and deploy agentic workflows that reduce manual effort, improve speed, and increase decision quality. Create or connect MCP servers that securely expose enterprise data, tools, and workflows to AI systems. Deliver rapid prototypes that can be validated by business users and converted into scalable implementations. Establish reusable patterns for AI agents, MCP integrations, RAG workflows, automation, and enterprise data access. Balance innovation with governance, security, documentation, maintainability, and measurable business value.