Lead AI Developer (Full-Stack)

We are looking for a Lead AI Developer to build an MVP test-intelligence platform that helps QA teams trust AI-driven semantic matching and classification across two game franchises. You will own AI/ML features end-to-end, including evaluation methodology and a data-heavy UI that explains scores and confidence.

Design and deliver end-to-end AI/ML application features across backend, evaluation harnesses, and frontend surfaces Build and maintain a semantic vector index service including gateway client integration, incremental embedding, normalization, HNSW indexing, and neighbor-query APIs Implement embedding backfill runs for multiple content streams with throughput controls and spend governance Design an evaluation corpus for semantic matching including label definitions, sampling methodology, and adjudication rules Run labeling passes and measure precision across confidence thresholds to set and validate gating criteria Implement a measured-confidence semantic matching route with off-until-measured gating and safety checks Build a semantic-to-deterministic link conversion pipeline that promotes high-confidence matches into durable links Implement a direct-delta observation route that derives signals from content-level changes when metadata links are sparse Develop an area-to-test translation bridge using LLM-assisted classification with batched calls, structured output, spend limits, and versioned proposal sets Create enrichment agents that classify and tag records and write results back into the unified data store Build a presentation layer with ranked test lists, reason chains, score breakdowns, overrides, and export flows Implement degraded-run detection, channel-health surfacing, and safety-net broadening rules for reliable operation 5+ years Python backend experience with FastAPI or equivalent frameworks 1+ years of relevant leadership experience Vector search experience with pgvector, HNSW index management, and similarity query design LLM API integration experience with batching, structured output, spend caps, and retry handling Embedding pipeline experience including text assembly, normalization, incremental embedding, and model versioning Semantic similarity evaluation experience including corpus design, label definitions, sampling, and precision measurement Data labeling methodology experience including disagreement rules, adjudication process, and labeling pass facilitation React frontend experience building data-heavy scoring and ranking interfaces Strong REST API development skills with OpenAPI contract adherence Advanced SQL skills including window functions and materialized views Strong Specification Driven Development (SDD) skills Strong problem-solving skills with attention to detail and measurement rigor Upper-Intermediate English proficiency (B2) Experience with enterprise AI gateways or Gemini embedding models Experience integrating QMetry, Zephyr, or QTM4J APIs Knowledge of Snowflake export pipeline design such as Snowpipe or bulk load Experience with LLM-based classification and reclassification pipelines Knowledge of gaming or AAA game QA workflows