Lead AI Engineer, Gtm Applications (remote)

CrowdStrike CrowdStrike · Enterprise · CA · Remote

Lead engineer for agentic AI solutions within GTM applications, focusing on building LLM-powered workflows, autonomous agents, and AI-enhanced integrations. Responsibilities include designing enterprise AI architecture, optimizing RAG systems, implementing evaluation frameworks, and mentoring engineers. Requires strong Python/TypeScript, experience with AI orchestration frameworks, Salesforce development, and vector databases.

What you'd actually do

  1. Lead engineering delivery for agentic AI capabilities for GTM stakeholders across its technology stack(Salesforce, Slack, 3rd party apps) and In-House Platforms.
  2. Design and build LLM-powered workflows, autonomous agents,multi-agent systems and AI-enhanced integrations using Agentcore, Slack, MCPs,Langchain
  3. Define scalable enterprise AI architecture patterns including model routing, orchestration,memory management and governance strategies
  4. Design and optimize Retrieval Augmented Generation(RAG) systems, semantic search pipelines,vector retrieval strategies and enterprise knowledge grounding frameworks.
  5. Implement AI evaluation frameworks including prompt quality benchmarking, hallucination reduction and model performance monitoring

Skills

Required

  • Python
  • TypeScript
  • Agentic AI frameworks
  • LLM powered systems
  • AI orchestration frameworks (LangGraph, Semantic Kernel, CrewAI, AutoGen, MCP, Langchain)
  • Salesforce development (Apex, LWC, REST/SOAP integrations, Platform Events, Agentforce)
  • vector databases
  • retrieval optimization techniques
  • AWS bedrock
  • Vertex AI
  • workflow orchestration
  • CI/CD tooling (GitHub Actions, Copado, Jenkins)
  • DevOps practices
  • LLM limitations
  • token economics
  • model selection trade-offs

Nice to have

  • Salesforce Platform Developer II or Application Architect certification
  • Slack apps development
  • Salesforce Einstein / Agentforce platform development
  • Contributions to open-source AI frameworks (LangChain, LlamaIndex)
  • fine-tuning
  • model evaluation
  • synthetic data generation
  • GTM AI datasets
  • model routing platforms
  • enterprise AI control planes

What the JD emphasized

  • agentic AI
  • autonomous agents
  • multi-agent systems
  • LLM-powered workflows
  • Agentcore
  • Langchain
  • RAG
  • vector databases
  • AI evaluation frameworks
  • prompt injection hardening
  • Agentic AI and LLM-powered tooling

Other signals

  • building the next generation of intelligent GTM workflows
  • lead hands-on engineering delivery of agentic AI solutions
  • prototype to production-grade AI-powered systems
  • Define scalable enterprise AI architecture patterns
  • Implement AI evaluation frameworks
  • Champion security-first AI engineering
  • Architect and implement CI/CD pipelines, deployment automation, and platform observability
  • Embrace Agentic AI and LLM-powered tooling as a core part of your engineering practice
  • Stay current with rapidly evolving AI/ML technologies and apply them pragmatically to GTM systems
  • Champion automation-first thinking
  • Build internal tools and apps to streamline data access and GTM decision-making
  • Implement data governance and monitoring frameworks
  • Evaluate vendors and AI platforms with a strategic build vs. buy mindset
  • Identify and automate manual processes