- Design and build a Java-based LLM service with a unified API serving multiple products, including the platform's player chat and help center
- Develop knowledge base ingestion pipelines, covering source parsing, chunking, embedding generation, incremental reindexing, and data versioning
- Build and optimize RAG pipelines and semantic search, including hybrid retrieval (vector search + BM25), reranking, source-grounded responses with citations, and multilingual query support
- Implement LLM guardrails to prevent prompt injection, protect personally identifiable information (PII), keep responses grounded in approved knowledge sources, and enforce iGaming-specific restrictions related to responsible gambling, identity verification, and payments
- Enable seamless handoff to human support agents and integrate the AI assistant with internal services through tool calling and structured outputs
- Build automated LLM evaluation pipelines using golden datasets, LLM-as-a-judge approaches, faithfulness and answer relevance metrics, and regression testing whenever prompts, models, or search indexes change
- Optimize LLM performance and operating costs through semantic caching, model selection based on query type, latency optimization, and token usage monitoring
- Implement production observability, including LLM tracing, quality dashboards, and business metrics such as automated resolution rate, escalation rate, and customer satisfaction (CSAT)

Requirements

- 4+ years of backend development experience with Java, including Java 17+, Spring Boot, REST/gRPC, Kafka or RabbitMQ, PostgreSQL, Redis, Docker, and Kubernetes
- Experience shipping at least one LLM-powered application to production with real users, and the ability to discuss its architecture, traffic, and quality metrics
- Hands-on experience building RAG systems, including chunking strategies, embedding model selection, hybrid retrieval, and reranking
- Ability to diagnose LLM response quality issues and distinguish between retrieval failures, prompt-related problems,



and model limitations
- Experience with vector databases and search engines such as pgvector, Qdrant, OpenSearch/Elasticsearch kNN, or equivalent technologies
- Experience integrating LLM provider APIs (OpenAI, Anthropic, Azure OpenAI, etc.), including function/tool calling, structured outputs, streaming, retries, model fallbacks, and rate limiting
- Experience evaluating LLM systems using quantitative metrics and automated evaluation frameworks such as Ragas, promptfoo, DeepEval, or custom evaluation datasets
- Strong software engineering practices, including automated testing, CI/CD, code reviews, logging, monitoring, and ownership of production services
- Nice to have experience with Spring AI or LangChain4j, along with familiarity with Python-based LLM frameworks such as LangChain or LlamaIndex and the ability to adapt their approaches to Java; experience with LLM observability tools such as Langfuse, Arize Phoenix, or OpenTelemetry; hands-on experience with semantic caching and LLM inference cost optimization; experience building multilingual AI assistants and knowledge base search systems; experience in iGaming, betting, FinTech, or customer support automation, including an understanding of industry-specific compliance requirements
- The opportunity to work on large-scale products and contribute to their development
- A flexible work environment built on autonomy, ownership, and trust, without micromanagement
- The option to work fully remotely or from a modern office
- Medical insurance coverage in countries where the company operates
- An annual $2,000 perks allowance after the probation period, which can be used for health insurance upgrades, language learning, and sports activities
- Partial reimbursement for professional training, courses, and participation in industry conferences
- Access to a corporate digital library
- Company-funded weekly online sessions with a psychologist
- Relocation opportunities to countries where the company has offices, with relocation assistance available after the probation period, subject to approval

#J-18808-Ljbffr

📌 AI Engineer IT (Australia)
🏢 01.tech
📍 Australia