AI Search Engineer
About The Position
Shade is seeking an AI Search Engineer to own the development and improvement of its AI search capabilities. This role involves building a multi-modal search engine that can find assets based on semantic meaning rather than just keywords, across various data types like vector embeddings, transcripts, metadata, and folder structures. The engineer will be responsible for designing and implementing indexing and retrieval pipelines that are both precise and cost-efficient at petabyte scale, integrating LLM re-ranking, and owning the evaluation harness. The position is crucial for enhancing Shade's core infrastructure, which includes a kernel-level distributed file system, data transfer tools, version control for creatives, and integrations with other creative tools.
Requirements
- 3+ years of full-time engineering experience.
- At least 2 years of experience owning AI search or information retrieval in production end-to-end.
- Strong Python experience, including building and maintaining backend services and data pipelines.
- Hands-on experience with LLM-powered search: RAG, re-ranking, hybrid retrieval, embeddings.
- Experience operating vector pipelines at scale: chunking, metadata enrichment, backfills, continuous re-indexing.
- Experience building eval harnesses and measuring retrieval quality.
- Ability to ship and maintain high volumes of quality code.
- Experience at a pre-Series B startup.
Nice To Haves
- Experience with MCP server work.
Responsibilities
- Own the end-to-end development of AI search capabilities at Shade.
- Design and implement indexing and retrieval pipelines for multi-modal search (vector, transcript, metadata, folder structure).
- Build and optimize LLM re-ranking layers for business-specific search intent.
- Develop and maintain cost-efficient search solutions at petabyte scale.
- Own the evaluation harness for measuring retrieval quality.
- Integrate AI search functionalities with the existing Python backend and C++ components.
- Make architectural decisions regarding caching, re-indexing frequency, and chunking strategies.
- Ensure search pipelines are precise and cost-efficient, maintaining high gross margins.
- Collaborate with the team to enhance data transfer, version control, and tool integrations.
Benefits
- Free lunch (under $30)
- Free dinner (under $30) if you stay more than 9 hours
- Fully covered health insurance, including dental and vision
- 401k with % match
- Unlimited PTO
- Lifetime gym membership
- Commuter benefit for the subway
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
Education Level
No Education Listed
