Senior Java Software Engineer - Search Inference - Platform

About the role

Elastic is hiring a Senior Java Software Engineer to work on the Elasticsearch Inference API, the layer that connects Elasticsearch with Elastic's own inference service, third-party model providers (Anthropic, OpenAI, Cohere, Google) and self-hosted models. The work powers semantic search, reranking and generative AI features.

What you'll do

• Build and maintain integrations with internal systems and external inference providers, covering schema negotiation, SSE streaming and error normalization
• Evolve the inference plugin architecture: task settings, chunking strategies, rate limiting and provider configuration
• Review open source contributions and work with external engineers to uphold technical standards
• Write unit tests with ESTestCase, YAML-based REST integration tests and rolling-upgrade tests
• Join the on-call rotation for inference-related incidents

Requirements

• 5+ years of production Java experience within large, established codebases
• Strong grasp of low-level Java: concurrency, parallelism, classloaders and modern language features
• Experience designing ergonomic APIs and reasoning through tradeoffs
• Proven use of AI tools to speed up development, debugging and optimization while owning outcomes
• Autonomy and clear asynchronous communication in a distributed team

Bonus: JDK internals, ML systems, open source ownership, Gradle, platform team experience.