Hi, I'm Christina Jia. I build AI agents
that ship to production.

Turn-level attribute mining + concept clustering over thousands of production customer dialogues (NER, intent, knowledge-grounding signals).

Custom ranking (failure_lift / success_lift) surfaces highest-impact agent errors — validated against human annotations across 5 rating tiers.

Traffic-matched user simulator enables closed-loop agent improvement without fresh live conversations.

Long-lived multi-agent daemon — PID locking, signal handling, launchd batch jobs, structured incident logs, shell-level command interception.

5-layer memory (SQLite FTS5 + ChromaDB): sub-100ms recall at 100K+ entries with daily GC and graceful degradation.

3-layer rate limiting + circuit breakers keep misbehaving agents inside API quota.

Three-stage YOLOv8 pipeline (hold detection, 5-class type, volumes) — mAP50 0.825 on hold detection.

Exported to ONNX, quantized to TensorRT FP16 on Jetson Nano — 12 FPS single-stage, 5 FPS full pipeline.

A* beta solver with scale-invariant reach recommends optimal move sequences via a Flask MJPEG WebUI.

LLM agent orchestrates macro analysis, multi-factor scoring, RL portfolio optimization, and news — behind a schema + risk + anomaly validation layer.

Multi-model routing picks vendor and model size per task — under $15/month for weekly rebalancing over a 100-stock universe.

Every decision recorded as a structured audit log for offline post-mortems and prompt/policy refinement.

Lease-based distributed lock with fault-tolerant renewal across crash and message-loss failure models.

TLA+ spec model-checked with fault injection — mutual exclusion, lease validity, and monotonicity invariants proven.

Property-tested the Python implementation with Crosshair, surfacing race conditions in lease handoff.

Real-time multimodal pipeline — Pinyin parsing, error correction, ranking, and speech/image feedback under <1s end-to-end latency.

Trie retrieval + probabilistic correction + LLM fallback rerank reach >95% accuracy on noisy input.

Async LLM calls with non-blocking UI and fallbacks on resource-constrained hardware.