An engineer who can build AI products from idea to production.
I am Wang Jianjun, an AI Engineer building intelligent systems with LLMs, agents and multimodal AI. I work across the stack — problem framing, system architecture, MCP tool governance, RAG and eval loops — through to enterprise deployment.
My focus is turning real business problems into production AI systems, not prototypes.
Capabilities in practice
Check delivery validity, evidence coverage and requirement fidelity for editable design artifacts, then repair findings and rerun the same case.
Business-First Delivery
The ultimate success metric of an AI system is not generation volume, but whether it reliably reduces costs and amplifies throughput in real operations.
Strict Tool Contracts & Governance
Tool invocations must enforce strict schema validation, deterministic structural outputs, and clear circuit breakers to prevent cascading hallucination.
Triple-Layer Verifiable Evals
A single HTTP 200 or non-empty string is not acceptance. We combine native structural validation, rendered visual proof, and business requirement audits.
Obsessive Traceability & Regressions
Freezing prompt context, decision traces, intermediate artifacts, and error snapshots ensures sporadic failures can be diagnosed and regression-tested.
Designing and building agentic systems that reason, retrieve, edit and act.
Building verifiable benchmarks, hybrid retrieval and data flywheels.
Shipping reliable, concurrent backend systems and toolchains.
Turning complex requirements into verifiable, regressible production capability.
CompliPilot: contributed compliance retrieval, citation verification and product engineering, connecting analysis to regulation sources.
Led LabMemory, connecting lab discussions, human confirmation and pre-action auditing through trusted decision memory.
Led product and engineering for TwinBuddy, matching travel companions through digital personas and bilateral agent negotiation.
Applied generalized additive models to statistical modeling and optimization of NIPT timing and quality control.
Used genetic algorithms for multi-objective modeling and parameter search in LED spectral optimization.
Contributed market research and TabNet data modeling for drone delivery.