Senior Java Software Engineer – Search Inference – Platform

Overview

In this role you will contribute to the Elasticsearch Inference API, building integrations with external ML providers and shaping the plugin architecture. You will work with cross-functional teams to deliver scalable, reliable inference capabilities for semantic search and generative AI. You’ll participate in on-call rotations and write thorough tests to ensure robust delivery. This is an opportunity to impact how Elastic brings AI-powered search to customers at scale.

Pay / Benefits

• Health coverage
• Flexible location and schedules
• Generous vacation days
• Donation matching
• Volunteer hours
• Parental leave

Responsibilities

• Build and maintain integrations with internal systems and external inference providers, including streaming and error normalization
• Contribute to the inference plugin architecture, including task settings, chunking, rate limiting, and provider configuration
• Review open source contributions to align with Elastic standards
• Participate in on-call rotation for inference incidents
• Write unit tests (ESTestCase), REST integration tests, and rolling-upgrade tests

Key requirements

• 5+ years of production Java experience
• Strong knowledge of core Java, data structures, and concurrency
• Experience crafting ergonomic APIs and reasoning about tradeoffs
• Experience with low-level Java concepts (concurrency, parallelism, classloaders)
• Proven ability to collaborate跨-functionally and work autonomously in a distributed team
• Ability to drive decisions and deliver results through asynchronous communication

• 跨-function collaboration
• autonomy
• clear communication
• problem-solving
• adaptability
• Java, concurrency, data structures

…