Data Engineer for AI Pipelines & Search — Equity + Visa

Solve Intelligence; Greater London; On-site; GBP 70,000 - 90,000; Full time

Benefits offered by this job

Equity stake

Founding impact

Visa sponsorship

Private medical insurance

Free meals

Job summary

Solve Intelligence is building the ingestion and search backbone for AI products across patent literature, case law, standards and scientific data. You will own end-to-end pipelines from source acquisition to serving queries, handling large, varied datasets with high throughput and reliability.

You'll collaborate with AI researchers and product engineers, owning schema design, indexing and performance optimisations to enable fast, scalable search across hundreds of millions of records.

Qualifications

• Strong Python and SQL; experience designing and operating production databases.
• Experience building and operating production data pipelines over large, messy datasets.
• Expertise with running search systems over large document collections.
• End-to-end ownership from raw data to user-facing functionality.
• Understanding of schema design, indexing and query optimisation.
• Experience diagnosing and fixing performance bottlenecks in live systems via profiling and measurement.

Responsibilities

• Large-scale ingestion: build and operate high-throughput pipelines for large datasets with incremental updates and recovery.
• Document processing and data quality: extract content, handle malformed records, validate outputs while preserving structure.
• Search and serving: build keyword, vector and structured search; design schemas and partitioning for fast queries.
• Connecting information across sources: link patents and records with traceability to sources.
• Performance engineering: profile parsing, ingestion, DB builds and queries; optimize for throughput, latency and cost.

Skills

Python

SQL

Data pipelines

Search systems

Performance optimization

Tools

PostgreSQL

pgvector

OpenSearch

Spark/Delta Lake

AWS

Job description

Solve Intelligence is building the ingestion and search backbone for AI products across patent literature, case law, standards and scientific data. You will own end-to-end pipelines from source acquisition to serving queries, handling large, varied datasets with high throughput and reliability.

You'll collaborate with AI researchers and product engineers, owning schema design, indexing and performance optimisations to enable fast, scalable search across hundreds of millions of records.