Salary
💰 $120,000 - $165,275 per year
Tech Stack
AWSAzureCloudGoogle Cloud PlatformPython
About the role
- Build, design, and maintain foundational LLM infrastructure, tooling, and reusable libraries to enable product teams
- Operationalize observability tools like LangSmith and create shared patterns for orchestration frameworks
- Deploy and build pipelines for vector databases to enable Retrieval-Augmented Generation (RAG) across product teams
- Contribute to proofs-of-concept and architectural groundwork for future-state LLM capabilities
- Add logging, monitoring, and alerting to platform services to ensure stability, performance, and cost-effectiveness
- Partner with feature teams as a consultant and enabler to understand needs and unblock AI roadmaps
- Deliver roadmap items on schedule and produce high-quality technical designs and maintainable code
- Mentor and share knowledge to improve internal processes and developer enablement
Requirements
- Demonstrated experience building and delivering production-grade software, with hands-on experience in LLM or Generative AI engineering
- Experience building internal tools, libraries, or platforms and strong API design and documentation skills
- Strong proficiency in Python
- Familiarity with modern AI/ML stack, including cloud services (AWS, GCP, or Azure) and CI/CD pipelines
- Hands-on experience with orchestration frameworks (e.g., LangChain, LangGraph) and observability tools (e.g., LangSmith)
- Experience with Retrieval-Augmented Generation (RAG) infrastructure and vector databases
- Ability to design, build, and maintain LLM infrastructure, tooling, logging, monitoring, and alerting
- Pragmatic problem-solving, risk identification, and sprint planning skills
- High degree of grit, ownership, and ability to work in fast-paced high-growth environments
- Bachelor's degree in a technical field or equivalent practical experience
- Deep understanding of handling sensitive data, security and privacy awareness