Senior Java Software Engineer (Search Inference, Platform)

• We are on the lookout for a Senior Java Developer to join our Elasticsearch team and drive our work on the Inference API in Elasticsearch
• The Elasticsearch Inference API is the integration layer between Elasticsearch and external machine learning services including Elastic’s own Elastic Inference Service (EIS), third-party providers (Anthropic, OpenAI, Cohere, Google), and self-hosted models. It powers features like semantic search, reranking, and generative AI across Elastic Cloud and in hosted environments
• You’ll maintain and develop the plugin framework and REST API with your work spanning protocol design, streaming, async execution, billing integration, and with a tight collaboration with the wider inference team and the Kibana team
• 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 work with third party engineers to ensure their contributions meet our technology standards
• Participate in on-call rotation for inference-related incidents
• Write thorough tests: unit tests using ESTestCase, YAML-based REST integration tests, and rolling-upgrade tests

Benefits

• Toast to your health: Fully paid health coverage for you and your family, in many locations.
• Craft your calendar: Flexible location and schedule for most roles.
• Create space for you: Distributed by design workforce, plus generous number of vacation days each year.
• Embrace parenthood: Minimum of 16 weeks of parental leave, plus generous family formation benefits.
• Give back your time: 40 hours each year to use toward volunteering with organizations and causes you’re passionate about.
• Amplify your impact: Double your charitable giving — we match donations up to $1500 USD (or local currency equivalent).

• 5+ years of production Java experience, with experience contributing to a large, established Java codebase. You know core Java and are conversant in the standard library of data structures and concurrency constructs, as well as newer language features
• You can work autonomously, drive decisions and results in a distributed team by leveraging asynchronous, direct, and transparent communication
• You possess the ability to collaborate across functions and teams and seamlessly transition between different projects, codebases, or teams based on business priorities
• Experience with low-level Java such as concurrency, parallelism, classloaders, etc
• Experience crafting ergonomic APIs and the ability to reason through trade-offs
• You have a proven track record of using AI to accelerate development, debug complex systems, and optimize code, while still owning the final outcomes
• Knowledge of Java build tools (Gradle, Maven, etc.), with a strong preference for Gradle experience
• Experience working in a platform team or developer productivity team
• Contributions to and ownership of open source projects
• Experience with ML systems
• Knowledge of JDK internals: modules, the Java memory model, garbage collection, database load, caching techniques, etc