Staff Software Engineer, TLM

About The Role

To create and advance a foundational AI infrastructure for the Developer Platform. This involves ensuring the development of robust systems for context, knowledge, and memory management, which are critical for enhancing AI-driven development experiences and improving agent functionality.

Success Metrics

• Increased accuracy and effectiveness of AI agents through enhanced data context and knowledge systems.
• Enhanced developer productivity by providing immediate access to accurate and useful information.
  
  

What You'll Do

• Team Leadership: Lead and mentor a small team of 4-5 AI engineers, fostering a collaborative and innovative work environment.
• Memory Systems Management: Design and manage shared memory systems, including the development of rules and best practice registries for AI agents.
• AI Documentation: Implement and oversee strategies for AI-first documentation generation, ensuring the health and discoverability of documentation.
• Code Context Infrastructure: Maintain repository and module summaries, providing comprehensive context for AI agents.
• Knowledge Graph & Data Ingestion: Vectorize engineering data and create knowledge graphs to facilitate advanced knowledge retrieval.
• Tooling and Client Development: Develop and maintain MCP servers/clients and other tools critical for enhancing the AI Developer Experience.
• Collaboration and Integration: Engage with AI Platform and AI DevEx teams to ensure seamless integration and alignment with broader organizational goals.
  
  

What You'll Need

Educational Background: Hold a degree in Computer Science, Artificial Intelligence, Machine Learning, or a closely related field.

Expertise in Large Language Models (LLMs): Demonstrated experience with both unimodal and multimodal LLMs and agentic systems.

Framework Proficiency: Skilled in using frameworks such as CrewAI, LangChain, and LangGraph to facilitate autonomous decision-making and workflow automation.

Emerging AI Technology Awareness: Knowledgeable about emerging AI technologies, including agentic systems, MCP, and A2A protocol, and understanding their potential applications.

Programming Skills: Proficient in writing clean, elegant, and bug-free code, particularly in languages such as Java and Go.

Problem-solving Abilities: Possess exceptional analytical and problem-solving skills with a focus on delivering scalable solutions.

Leadership and Mentorship: Ability to mentor junior engineers and actively contribute to team development and growth.

Preferred Qualifications

Cloud Computing Knowledge: Proficient in utilizing cloud computing infrastructure to support scalable AI/ML applications.

AI/ML Framework Expertise: Experience with leading AI/ML development frameworks and tools, including TensorFlow, PyTorch, and Hugging Face, for building advanced AI solutions.

AI Monitoring and Observability: Familiarity with AI monitoring and observability tools such as Langfuse, Prometheus, and Grafana, or similar platforms to ensure effective system performance and management.

Vector and RAG Models: Skilled in embedding generation and retrieval using VectorDB and RAG ingestion techniques for enhancing AI data processing capabilities.