Senior Java Software Engineer - Search Inference - Platform
Core
Develop and maintain the Inference API in Elasticsearch, serving as the integration layer between Elasticsearch and external machine learning services to power semantic search, reranking, and generative AI features.
Role type
Senior Java Software Engineer (Search Inference Platform)
Builds
Elasticsearch Inference API, plugin framework, and integrations with internal systems and external ML providers (Anthropic, OpenAI, Cohere, Google).
Domain
Search technology, Machine Learning infrastructure, Cloud platforms
Deliverable
production ML models
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, Schema negotiation, Error normalization, Rate limiting, Provider-level configuration
Preferred skills
JDK internals (modules, memory model, GC), ML systems knowledge, Gradle, Platform team experience
Responsibilities
Build and maintain integrations with internal systems and external inference providers; Contribute to the inference plugin's internal architecture; Review open source contributions; Participate in on-call rotation for inference-related incidents; Write thorough tests (unit, integration, upgrade).
