As a Lead AI Engineer, you'll guide a multidisciplinary team of 4-8 engineers focused on developing core intelligence capabilities for a next-generation platform. Your work will center on creating systems that maintain long-term user context and deliver timely, relevant insights through proactive monitoring and summarization.
Role Responsibilities
- Lead a technical pod spanning AI/LLM and backend infrastructure, balancing hands-on development with engineering leadership
- Design and implement persistent memory architectures that retain and apply user knowledge across sessions
- Build intelligent alerting systems that detect meaningful changes, summarize key updates, and route information efficiently
- Collaborate closely with adjacent teams to define integration points with AI agent pipelines and communication channels
- Own the technical roadmap while contributing directly to production code, with over half your time spent coding
- Establish system contracts and APIs to ensure seamless interoperability across services
What You Bring
- Seven or more years of professional software development using Python
- Proven experience deploying LLM-driven applications in production environments
- Track record of leading engineering teams while remaining deeply involved in implementation
- Strong foundation in asynchronous processing, event-driven design, and scheduled job systems
- Ability to navigate ambiguous problems and build robust solutions from the ground up
- Experience unifying AI and infrastructure disciplines to deliver cohesive systems
Preferred Expertise
- Building systems that evolve user state and context over time
- Working with semantic search, vector databases (e.g., Pinecone, Weaviate, Snowflake Cortex), and embedding technologies
- Implementing change detection and event-driven workflows
- Using observability tools for LLM applications such as Langfuse, LangSmith, or Weights & Biases
- Forming new engineering teams and establishing technical direction from inception
Environment & Culture
This role is part of a forward-thinking intelligence initiative within a globally recognized research and advisory organization. You'll work alongside curious, high-performing peers in a culture that values rigor, collaboration, and integrity. The environment encourages growth, supports individual initiative, and enables engineers to explore beyond their core domain.
The position operates under a hybrid model, with an expectation of 1–2 days per week on-site. You’ll have the autonomy to shape new capabilities while contributing to a platform where innovation leads directly to impact.
