Responsibilities:

• Own end-to-end design, development, and continuous improvement of Deep Research Agent
• Design and maintain RAG pipeline including chunking strategy, embedding models, retrieval, and re-ranking
• Implement and optimize context compression for long-horizon, multi-hop queries
• Build and operate model evaluation harness with benchmark design, regression tracking, and A/B testing
• Lead agent self-improvement loop with prompt proposal pipeline and benchmark-gated merge governance
• Track frontier model research and assess production applicability for platform intelligence roadmap
• Advise on fine-tuning, prompt optimization, and model selection strategies across model generations

More skills:

fine-tuning (LoRA/QLoRA), RLHF, alignment techniques, RAG system design, vector databases (Pinecone, Weaviate, pgvector), ML experimentation tooling, Vertex AI Experiments, Python ML stack, PyTorch, JAX, HuggingFace Transformers, statistical evaluation methods, benchmark design, significance testing, evaluation dataset curation, context compression, KV cache optimisation, quantisation basics (GPTQ, AWQ)

Other:

• Opportunity to push boundaries and build innovative solutions
• Work in a diverse and inclusive team environment
• Equal Opportunity Employer
• Encouragement for applicants from all backgrounds