Senior Java Software Engineer - Search Inference - Platform

In this role, you will advance the Elasticsearch Inference API by building and maintaining integrations with ML providers and internal systems. You’ll contribute to the plugin framework and REST API, collaborating with the inference and Kibana teams to enable semantic search, reranking, and generative AI across Elastic Cloud. You will shape architecture, ensure robust streaming and error handling, and own high-quality tests and operating reliability. This is a chance to impact AI-powered search at scale in a distributed, product-focused environment.

• competitive pay
• health coverage for you and family
• flexible locations and schedules
• generous vacation days
• donation matching up to $2000
• volunteer time off

• Build and maintain integrations with internal systems and external inference providers, including schema negotiation, streaming (SSE), and error normalization
• Contribute to the inference plugin's internal architecture: task settings, chunking strategies, rate limiting, and provider-level configuration
• Review open source contributions to the codebase and coordinate with third-party engineers to meet standards
• Participate in on-call rotation for inference-related incidents
• Write thorough tests: unit tests with ESTestCase, YAML REST integration tests, and rolling-upgrade tests

• 5+ years of production Java experience in a large, established codebase
• Strong core Java knowledge and data structures/concurrency understanding
• Experience crafting ergonomic APIs and evaluating tradeoffs
• Proficiency with low-level Java concepts including concurrency and classloaders
• Proven track record of using AI to accelerate development and optimize code
• Ability to collaborate across functions and teams and adapt to multiple projects
• Ability to work autonomously and drive decisions in a distributed team using asynchronous communication

• collaboration across teams
• autonomous and proactive work style
• clear, direct communication
• Java proficiency in production environments
• API design experience
• concurrency and parallelism expertise