Senior Java Software Engineer - Search Inference - Platform
Core
Build and maintain the Elasticsearch Inference API, serving as the integration layer between Elasticsearch and external machine learning services (Elastic Inference Service, Anthropic, OpenAI, Cohere, Google) to power semantic search, reranking, and generative AI.
Role type
Senior Java Software Engineer (Search Inference Platform)
Builds
Elasticsearch Inference API, plugin framework, and REST API for cloud and hosted environments
Domain
Search technology, Machine Learning integration, Cloud infrastructure
Deliverable
production ML models (via careerplan.io/jobs/8237962-senior-java-software-engineer-search-inference-platform-at-elastic)
Required skills
Java (core, concurrency, parallelism, classloaders), REST API design, Protocol design, Streaming (SSE), Async execution, Unit testing, YAML-based REST integration testing, Rolling-upgrade testing, Open source contribution review
Preferred skills
JDK internals (modules, memory model, GC), ML systems knowledge, Gradle, Platform team experience
Technologies
Elasticsearch, Elastic Inference Service, Anthropic, OpenAI, Cohere, Google, Gradle, Maven, ESTestCase
Responsibilities
Develop and maintain integrations with internal systems and external inference providers; Contribute to the inference plugin's internal architecture (task settings, chunking, rate limiting); Review open source contributions; Participate in on-call rotation for inference incidents; Write thorough tests (unit, integration, upgrade)
Seniority
Senior, hands-on IC
