Description:

ThirdLaw is building the control layer for AI in the enterprise, addressing safety, compliance, and operational risks associated with AI adoption.
The company helps IT and Security teams determine if AI behavior is acceptable and enables real-time action when it is not.
The role involves building and scaling systems that reconcile latency, correctness, and observability across distributed pipelines.
Responsibilities include architecting scalable, low-latency services for real-time and batch evaluations, integrating with streaming data pipelines.
The engineer will design and build the core evaluation engine that detects violations across LLM inputs and outputs.
A runtime intervention layer will be created to execute enforcement actions based on evaluation results and risk context.
The position requires creating reusable frameworks for pluggable evaluators and intervention policies, supporting no-code authoring and automated deployment.
The engineer will configure and operationalize a vector database pipeline for RAG-like use cases and implement reliability controls for scalability.

Requirements:

Candidates must have 5+ years of backend software engineering experience, including designing and shipping production software services.
Strong coding proficiency in Python and/or Go is required.
Deep experience with streaming data pipelines (e.g., Kafka, Pulsar, Redis Streams) and batch processing systems is necessary.
A proven track record of scaling high-QPS, low-latency services is essential, with p95/p99 ownership being a plus.
Familiarity with vector databases (e.g., FAISS, Weaviate, Qdrant, pgvector) and embedding-based matching is required.
A strong grasp of cloud-native infrastructure, including containers, Kubernetes, serverless functions, and CI/CD pipelines, is needed.
Exposure to structured observability patterns, such as OpenTelemetry or similar tracing standards, is important.
Candidates should be comfortable designing and defending trade-offs around build vs buy vs OSS.

The position offers the opportunity to work on innovative projects that shape the safe deployment of AI technologies.
Employees will be part of a small, focused team that values autonomy and real impact over titles and management.
The role encourages proactive mindsets and clear written communication, with a strong emphasis on asynchronous work.
Team members will have the chance to work closely with customers to shape products and contribute to the mission of ensuring AI trust and safety.