Senior Machine Learning Engineer, Search & Index
About The Position
Wayve is seeking a Senior Machine Learning Engineer for its Search & Indexing team. This role is crucial for making Wayve's extensive multimodal video data discoverable and searchable. The team is responsible for building the indexing infrastructure that supports both vector-based and metadata-based retrieval, which is essential for high-leverage workflows in data curation, training set construction, and ML research. The engineer will collaborate with the Technical Lead and peers to scale and enhance the system that manages retrieval across hundreds of thousands of hours of driving data. Key contributions will include architectural decisions, ownership of complex components, and defining best practices as the team expands. A primary focus is on launching the next iteration of the indexing stack, which will enable similarity search and metadata filtering across vast amounts of video and sensor data. The immediate goal is to rapidly deploy an MVP system by leveraging off-the-shelf tools and informing build vs. buy decisions. This position requires an individual comfortable with ambiguity, technically pragmatic, and capable of making sound architectural choices in challenging conditions. The role involves close collaboration with ML teams, platform engineers, and downstream users to transform indexing from a bottleneck into a core capability.
Requirements
- 7+ years of experience in backend, infrastructure, or ML systems, building production systems.
- Experience with vector databases or ANN technologies such as FAISS, LanceDB, or similar open-source solutions.
- Strong understanding of multimodal embeddings and experience evaluating search quality across relevance, recall, filtering accuracy, and performance.
- Strong coding skills in Python or other systems languages.
- Experience building search services, APIs, and large-scale ingestion and indexing pipelines.
- Experience delivering 0→1 systems in ambiguous or exploratory problem spaces.
- Comfortable working across system boundaries (infra, ML, data curation).
Nice To Haves
- Experience with large-scale ML pipelines or distributed data infrastructure.
- Familiarity with multimodal data, including video, images, sensor data, and metadata.
- Exposure to active learning, semantic retrieval, or training-data selection workflows.
- Prior experience in autonomy, robotics, or large-scale data infrastructure.
- Experience evaluating technical vendors and working with external technology providers.
Responsibilities
- Build and operate production search and indexing systems at billion-vector scale.
- Apply and evaluate embedding models for semantic and multimodal retrieval, including inference, normalization, versioning, and integration.
- Build evaluation frameworks to measure retrieval quality, recall, relevance, filtering accuracy, latency, freshness, scalability, and cost.
- Develop backend services and APIs for vector similarity and metadata-filtered search.
- Own search components from design and implementation through deployment and production operations.
- Collaborate with ML, Data, and Evaluation teams to integrate search into training, curation, and evaluation workflows.
- Support the growth of other engineers through code reviews, technical guidance, knowledge sharing, and mentoring.
Benefits
- Competitive equity package
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
