GTM Engineer

• →Develop and implement end-to-end GTM strategies and processes within a B2B SaaS environment.
• →Create and optimize multi-system workflows and automations using REST APIs and event-driven integration patterns.
• →Design and deploy serverless applications and event-driven architectures using AWS services.
• →Build and integrate AI agents and workflows using Amazon, Claude/Anthropic models, and approved business systems.
• →Collaborate with stakeholders to translate business problems into effective technology solutions.
• →Ensure AI agents and workflows meet standards for accuracy, reliability, scalability, and security.
• →Contribute to the development of standards for AI agent lifecycle management and observability.

• 6+ years of experience working directly with GTM processes and systems in a B2B SaaS or technology environment.
• Strong understanding of end-to-end Lead-to-Revenue and customer lifecycle processes.
• Demonstrated understanding of Sales, Marketing, Customer Success, and Revenue Operations workflows.
• Strong understanding of core SaaS commercial concepts and metrics.
• Experience translating business problems into process and technology solutions.
• Demonstrated ability to work directly with business stakeholders and challenge or refine requirements.
• Experience working across multiple GTM platforms and understanding cross-system dependencies.

• Strong understanding of REST APIs, webhooks, JSON, OAuth, authentication, and event-driven integration patterns.
• Experience designing multi-system workflows and automations.
• Experience with workflow orchestration technologies.
• Ability to evaluate when low-code/no-code automation is appropriate versus custom development.
• Experience with platforms such as Zapier, n8n, Workato, Make, Tray.io, or comparable technologies is beneficial but not required.
• Experience with web scraping, browser automation, data extraction, or related technologies is beneficial.
• Ability to quickly learn and evaluate emerging automation and data acquisition technologies.

• Hands-on experience with AWS Lambda and serverless application patterns.
• Experience with AWS Step Functions or comparable workflow orchestration concepts.
• Experience with Amazon EventBridge and event-driven architecture.
• Experience with Amazon Bedrock or demonstrated experience building applications using foundation-model APIs.
• Familiarity with API Gateway, CloudWatch, IAM, Secrets Manager, S3, queues, databases, and related AWS services.
• Understanding of cloud security, permissions, monitoring, and production support practices.

• Design, build, and deploy AI agents and AI-enabled workflows within the approved architecture.
• Use Amazon and Claude / Anthropic models for reasoning, classification, summarization, research, recommendations, and decision support.
• Build agentic workflows combining LLM reasoning with structured business data, APIs, deterministic rules, web-derived information, and approved tools.
• Integrate agents with approved business systems and data sources through available APIs, connectors, and Model Context Protocol (MCP) capabilities.
• Understand how to discover, configure, and use available MCP servers and tools within AI workflows.
• Evaluate when an existing MCP capability can simplify access to a system or data source rather than building a custom integration.
• Design prompts, context, structured outputs, tool/function calling, guardrails, and human-in-the-loop patterns.
• Determine when deterministic workflow logic should be used instead of an LLM or agent.
• Test agents and workflows for accuracy, reliability, security, latency, scalability, cost, and measurable business value.
• Contribute to standards for agent permissions, observability, evaluation, and lifecycle management.

Candidates should have hands-on experience with or strong practical knowledge of:

• Claude / Anthropic and/or other leading foundation models
• Prompt and context engineering
• Structured outputs
• Tool / function calling
• Agentic workflows and AI orchestration
• Model Context Protocol (MCP) concepts and use of MCP-enabled tools
• Connecting AI workflows to approved systems and data sources
• Retrieval-Augmented Generation (RAG) concepts
• Human-in-the-loop patterns
• Model and agent evaluation
• AI observability
• AI security, guardrails, data privacy, and responsible AI

Prior MCP experience is beneficial but not required. Candidates should be able to quickly learn and leverage MCP-enabled capabilities as part of AI and automation workflows.