H Company is hiring a Senior Senior Applied Scientist — Search & ranking on the Marketplace relevance team (Hybrid · London, United Kingdom). This is a hands-on role in search & recommendations—not a generic “AI enthusiast” post.
You will own ranking, retrieval, and online experimentation end to end: problem framing, offline evaluation, safe rollout, and iteration from production signals. Success is measured with clear metrics (quality, latency, cost, or business KPIs)—not slide decks alone.
London hybrid team blends classical learning-to-rank with embeddings and GenAI-assisted summaries. We optimise for buyer trust, seller fairness, and measurable GMV lift—not vanity offline metrics.
You will collaborate with PM, search infra, and marketplace integrity squads.
What you will do
- Design offline metrics that mirror online constraints; lead power analysis for experiments.
- Prototype ranking changes with guardrails for cold start, diversity, and abusive listings.
- Coordinate model handoffs: feature contracts, monitoring, and rollback plans.
- Present readouts to GM-level stakeholders with crisp storytelling.
- Mentor junior scientists on causal pitfalls and Simpson’s paradox in two-sided markets.
What we look for
- PhD/MS in quantitative field or equivalent industry depth in search/recommendations.
- Python + SQL + PyTorch; large-scale logging and experimentation platforms.
- 5+ years owning ranking models in prod.
Nice to have
- Snowflake dbt analytics loops.
- Integrity / trust & safety collaboration experience.