Senior Java Engineer - Inference API for AI-Driven Search

Elastic; United Kingdom; On-site; GBP 90,000 - 130,000; Full time

Benefits offered by this job

Competitive pay

Health coverage for you and your loved

Flexible locations and schedules

Generous vacation days

Volunteer time (40 hours)

Parental leave (16 weeks)

Job summary

Elastic is seeking a Senior Java Developer to join the Elasticsearch team and advance the Inference API. You will design, implement, and maintain integrations with internal systems and external ML providers, focusing on performance, reliability, and scalable architecture across distributed environments.

You will work on protocol design, streaming, async execution, and collaborate with Kibana and broader inference teams.

Qualifications

• 5+ years of production Java experience, with large codebases.
• Ergonomic API design and trade-off reasoning.
• Strong knowledge of concurrency, data structures, and Java internals.

Responsibilities

• Build and maintain integrations with internal and external inference providers.
• Contribute to plugin architecture: settings, chunking, rate limiting, provider config.
• Review open source contributions and ensure code quality.
• Participate in on-call rotations for inference incidents.
• Write unit tests and integration tests (ESTestCase, YAML REST tests).

Skills

Java

APIs

Concurrency

Async

AI/ML acceleration

Tools

Gradle

Maven

ESTestCase

Job description

Elastic is seeking a Senior Java Developer to join the Elasticsearch team and advance the Inference API. You will design, implement, and maintain integrations with internal systems and external ML providers, focusing on performance, reliability, and scalable architecture across distributed environments.

You will work on protocol design, streaming, async execution, and collaborate with Kibana and broader inference teams.