Senior AI Engineer — LLM, RAG, & Multilingual Search

01.tech; Australia; Remote; AUD 140,000 - 210,000; Full time

Benefits offered by this job

Medical insurance

Benefits allowance

Training reimbursement

Digital library

Psychology sessions

Relocation assistance

Remote or office work

Autonomy & ownership

Job summary

01.tech is seeking a seasoned backend developer to design and build a Java-based LLM service with a unified API powering the platform's player chat and help center. You will own core infra and ship production features.

The role covers knowledge base ingestion, RAG pipelines, guardrails for safety and compliance (including responsible gambling), multilingual support, and seamless handoff to human agents. You will optimize costs and enable observability while collaborating across teams in a

Qualifications

• 4+ years backend development with Java (17+), Spring Boot, REST/gRPC, Kafka or RabbitMQ, PostgreSQL, Redis, Docker and Kubernetes.
• Experience shipping at least one LLM-powered production application with real users.
• Hands-on with RAG systems: chunking, embeddings, hybrid retrieval and reranking.
• Experience with vector databases and search engines (pgvector, Qdrant, OpenSearch/Elasticsearch kNN).
• Experience integrating LLM provider APIs (OpenAI, Azure OpenAI, etc.) with function/tool calling and structured outputs.
• Ability to evaluate LLM systems with quantitative metrics and automated evaluation frameworks.

Responsibilities

• Design and build a Java-based LLM service with a unified API for multiple products (player chat, help center).
• Develop knowledge base ingestion pipelines: parsing sources, chunking, embeddings, reindexing and data versioning.
• Build and optimize RAG pipelines and semantic search with hybrid retrieval and multilingual support.
• Implement LLM guardrails for prompt safety, PII protection, grounded responses, and iGaming compliance.
• Enable handoffs to human agents and integrate AI with internal services via tools and structured outputs.
• Create automated LLM evaluation pipelines using golden datasets and regression testing.
• Optimize performance and costs via semantic caching, model selection, latency tuning and token monitoring.
• Establish production observability with tracing, dashboards, and CSAT metrics.

Skills

Java

Spring Boot

REST/gRPC

Kafka/RabbitMQ

PostgreSQL

Redis

Docker

Kubernetes

LLM pipelines

RAG systems

Tools

pgvector

Qdrant

OpenSearch/elasticsearch kNN

LangChain4j

LangChain

LlamaIndex

OpenTelemetry

Job description

01.tech is seeking a seasoned backend developer to design and build a Java-based LLM service with a unified API powering the platform's player chat and help center. You will own core infra and ship production features.

The role covers knowledge base ingestion, RAG pipelines, guardrails for safety and compliance (including responsible gambling), multilingual support, and seamless handoff to human agents. You will optimize costs and enable observability while collaborating across teams in a