4 days ago
Responsibilities
- Own the end-to-end architecture and development of the Game Intelligence ML platform, including data ingestion, semantic layers, feature stores, model registries, evaluation, and serving.
- Build predictors for commercial game outcomes such as user acquisition cost, lifetime value, return on ad spend, and retention.
- Develop market-signal forecasting models, calibrated prediction ranges, ranking systems, and budget-aware portfolio recommendations.
- Define reproducibility and auditability practices using versioned data snapshots, model and prompt versions, and per-decision cost tracking.
- Design online experiments with guardrails, safe exploration, and explicit human decision points.
- Build evaluation harnesses for LLM-based agents, automated playtesting, and multimodal generated-content assessment.
- Orchestrate frontier-model agents in production with strict data boundaries and cost controls.
- Own feedback loops that measure realized outcomes, correct bias and signal weighting, and communicate prediction error clearly.
- Lead engineering practices for agentic development and evaluation, partner with cross-disciplinary teams, and shape the roadmap with product stakeholders.
Requirements
- Passion for the game industry and deep experience in game, game-engine, or game-publishing environments.
- Production machine learning or agentic-systems experience owning systems end to end from data through serving and measured business outcomes.
- Deep performance-marketing or ad-tech modeling experience, including acquisition cost, lifetime value, return on ad spend, retention, or comparable outcomes.
- Strong grounding in probabilistic prediction and calibration, including quantile or interval prediction, coverage, bias correction, and forecast backtesting.
- Production experience building LLM-based agent systems, including orchestration, evaluation harnesses, prompt and model versioning, and cost control.
- Experience working in a zero-to-one environment.
- Experience with mobile game user acquisition, LiveOps, monetization, Unity, automated or bot-driven playtesting, time-series forecasting, or noisy multi-source market signals is advantageous.
- Experience with the Claude Agent SDK, Codex, or similar multi-agent software-production frameworks is advantageous.
- Hands-on experience with BigQuery, ClickHouse, Kafka, Postgres, pgvector, or equivalent technologies is advantageous.
- Publications or open-source contributions in forecasting, causal inference, calibration, or agentic systems are advantageous.
Benefits
- Comprehensive health, life, and disability insurance, with eligibility and coverage varying by country and employment status.
- Commute subsidy, employee stock ownership, competitive retirement or pension plans, generous vacation and personal days, and new-parent and family-care leave programs.
- Office food snacks, mental health and wellbeing support, Employee Resource Groups, and a global employee assistance program.
- Training and development programs plus volunteering and donation matching.
Tech Stack
Categories
About Unity
Unity is a public software company that builds the Unity real-time 3D engine and services for creating, operating, and monetizing games and interactive 3D content across mobile, PC, console, and XR. It sells subscription licenses and usage-based services such as cloud build, ads, and analytics to studios and enterprises in gaming, automotive, film, and AR/VR. Founded in 2004 and headquartered in San Francisco, it trades on the NYSE (U).