Live opening · Posted 27 days ago
The key details from the original listing.
Live timing from JobBeeper.
Description supplied by the original job listing.
Responsibilities:
Implement end-to-end AI pipelines: data ingestion, embedding generation, retrieval, prompting, response processing, and evaluation.
Build and maintain RAG pipelines using vector databases (Pinecone, Weaviate, Qdrant, and pgvector) and retrieval frameworks.
Develop LLM integration layers: API orchestration, streaming, tool-calling, and structured output parsing.
Write evaluation harnesses to measure LLM output quality, latency, cost, and safety across prompt variations.
Use AI development tools (Cursor, GitHub Copilot, and Claude Code) to accelerate development and iterate effectively.
Collaborate with GenAI architects on system design; translate architecture specs into reliable, tested code.
Build internal and client-facing APIs that expose AI capabilities with proper auth, rate limiting, and observability.
Hands-on experience with at least one LLM framework: LangChain, LlamaIndex, or direct provider SDKs.
Understanding of vector search concepts, embedding models, and semantic similarity.
Comfort working in cloud environments (AWS/GCP/Azure); ability to deploy and monitor service.
Participate in code reviews and contribute to team standards for AI engineering best practices.
Requirements:
Strong problem-solving skills with the ability to debug complex AI pipeline failures.
Willingness to use and learn AI-augmented development workflows as a first-class engineering practice.
Experience
6-10 yrs
Recently tracked roles with full details and direct application links.