About The Position

We are seeking a Principal Engineer to lead the technical vision and long-term architecture of our GenAI Search Platform. This platform powers Moveworks’ conversational search and question-answering systems, combining advanced information retrieval with large language models (LLMs) to deliver instant, enterprise-grade answers at scale. As a Principal Engineer, you will operate at the intersection of search, generative AI, and platform infrastructure. You will define and drive the multi-year technical strategy for our search ecosystem — ensuring it is scalable, extensible, secure, and capable of supporting the next generation of agentic and LLM-enabled experiences across the enterprise. You will partner closely with ranking, ML, product, infrastructure, data science, and customer teams to evolve our search platform into a foundational capability that enables rapid innovation while maintaining rigorous guarantees around quality, privacy, and reliability.

Requirements

  • 8+ years of engineering experience, with a track record of leading large-scale technical initiatives across teams.
  • Demonstrated experience operating at Staff/Principal scope, driving architecture and influencing technical direction beyond a single team.
  • Deep expertise in search systems, information retrieval, ranking, recommendation systems, or large-scale question-answering platforms.
  • Strong background in text processing, natural language understanding, and/or applied machine learning.
  • Experience designing distributed systems that operate at enterprise scale with high reliability and performance requirements.
  • A systems thinker who balances innovation with pragmatism in production environments.

Nice To Haves

  • Experience with large language models, retrieval-augmented generation (RAG), or agent-based architectures.
  • Experience productionizing LLM systems with attention to cost, latency, evaluation, and safety.
  • Strong Python experience, particularly contributing to platform-level libraries or shared infrastructure.
  • Familiarity with Golang or other backend systems languages.

Responsibilities

  • Set Technical Vision & Architecture
  • Define and evolve the long-term architecture of our GenAI search platform, balancing classical information retrieval techniques with LLM-driven retrieval-augmented generation (RAG) systems.
  • Architect scalable abstractions and frameworks that enable multiple teams (ranking, product, ML) to safely and independently build on top of the platform.
  • Establish durable design principles for performance, enterprise readiness, extensibility, and observability.
  • Drive Next-Generation Search Capabilities
  • Lead the development of advanced conversational search systems, including multi-turn, multi-hop, and agentic workflows.
  • Define architectural patterns for integrating LLMs into search systems in a secure, cost-efficient, and production-grade manner.
  • Ensure the platform can support rapid experimentation while enforcing guarantees around security, privacy, and compliance in enterprise environments.
  • Platform Quality & Evaluation Strategy
  • Establish systematic evaluation methodologies and metrics for search and generative systems, including LLM-assisted evaluation frameworks.
  • Lead the definition of quality standards for ranking, retrieval accuracy, hallucination mitigation, and user trust.
  • Champion performance optimization, scalability, and operational excellence across the platform.
  • Cross-Functional Technical Leadership
  • Influence product and engineering roadmaps to align with platform strategy and long-term scalability goals.
  • Serve as a technical advisor across teams, ensuring architectural coherence and reducing fragmentation.
  • Drive high-leverage initiatives that unlock velocity for multiple product teams.
  • Organizational Impact
  • Mentor and elevate senior and staff engineers.
  • Shape hiring strategy and help close top technical talent.
  • Raise the bar for engineering excellence, documentation, design rigor, and code quality across the organization.
© 2024 Teal Labs, Inc
Privacy PolicyTerms of Service