Summary

What you’ll do:

• AI Infrastructure & Internal Tools

  • Architect, build, and maintain Jump’s internal AI platform — including model evaluation frameworks, experimentation, context and prompt management systems, and fine-tuning pipelines.
  • Standardize and automate internal tooling: from Claude code org wide setup to orchestration frameworks for AI agents and workflows.
  • Design and deploy RAG systems, vector databases and other foundational components for production-grade AI systems.
  • Define best practices for evaluation and benchmarking of models and agentic workflows (including quality, reliability, latency, cost, and safety).
  • Develop templates and libraries for agentic workflows, memory, and tool use.
  • Partner with the engineering organization to integrate AI agents and features into Jump’s products.
  • Ensure reliability, observability, and scalability of AI systems across environments.

• AI Organizational Enablement

  • Act as an AI subject matter expert — running workshops, demos, and internal talks to help every function apply AI to their workflows.
  • Lead rapid experimentation initiatives — identify and prototype high-impact internal AI use cases, then scale successful ones.
  • Partner cross-functionally with HR, Finance, and Client Services to design and deploy AI automations that save time and increase quality.
  • Maintain an internal AI playbook — a living repository of best practices, design patterns, and how-to guides for prompt engineering, context design, agent building, and evaluation.
  • Mentor engineers and product teams on effective use of LLMs, model selection, and architecture design.

What you’ll bring:

• 10 years in software engineering or systems architecture, with 1 years focused on AI/ML, LLMs, and agentic systems.
• Full stack development experience.
• Deep technical expertise with modern AI systems and frameworks — including Foundational models APIs, AWS Bedrock, N8N, Open Source Models, LangChain or similar.
• Proven experience building and deploying AI infrastructure, including evaluation frameworks, monitoring, and agentic workflows.
• Hands-on experience with vector databases, RAG systems, and context management for LLMs.
• Strong proficiency in Python and TypeScript, with experience integrating APIs and orchestration tools.
• Familiarity with cloud infrastructure (AWS), containerization (Docker, Kubernetes), and IaC (Terraform, CloudFormation).
• Experience fine-tuning LLMs.
• Excellent communication and presentation skills — comfortable leading demos, training sessions, and internal talks for both technical and non-technical audiences.
• A passion for teaching, experimentation, and scaling organizational impact through AI.

Nice to have (but not required):

• Experience building multi-agent systems.
• Contributions to open-source AI tools.
• Experience implementing internal developer platforms or productivity tools.