4 days ago
Responsibilities
- Own AI-assisted dissolution support from customer problem through production behavior, measurement, and iteration.
- Design retrieval, context, structured outputs, tool contracts, orchestration, and deterministic boundaries for grounded and inspectable behavior.
- Build useful answer, status, no-action, and human-handoff experiences for cases with incomplete evidence or authority.
- Create versioned evaluations for routing, grounding, usefulness, safety, stability, and real customer outcomes.
- Ship explicit permissions, tenant boundaries, privacy controls, auditability, canaries, rollback, and recovery.
- Instrument runtime and tool reliability, latency, cost, repeat contact, support effort, and serious failure modes.
- Convert production failures into durable product, evaluation, and system improvements.
- Decide whether complex workflows should be automated, AI-assisted, structured for a human, or remain human-owned, then build the approved approach.
- Work closely with Product, Support, Security, domain experts, and full-stack engineers on the surrounding Dissolution product.
Requirements
- Personally owned a production software product, including an LLM-backed capability beyond a prototype.
- Strong product engineering ability across customer experience, application code, backend systems, AI behavior, and production operations.
- Understanding of retrieval, context selection, structured outputs, tool use, orchestration, evaluation, and observability.
- Ability to define evidence, state, authority, permissions, privacy, escalation, rollback, recovery, and failure boundaries.
- Uses representative evidence to make ship, revise, or stop decisions rather than optimizing demos or a single aggregate score.
- Comfort working with Product, Support, Security, domain experts, and engineering partners.
- Fluent use of modern AI development tools with rigorous verification of their output.
- Bonus: experience with customer-support, operations, or multi-step workflow agents.
- Bonus: experience with LangGraph, LangChain, typed tool protocols, retrieval systems, golden datasets, offline evaluation, shadow deployments, or model-based judges.
- Bonus: experience with privacy-sensitive, multi-tenant, audited, legal, financial, or other high-trust products.
- Strong Python plus TypeScript, React, Node.js, or comparable full-stack experience.
Tech Stack
Categories
AI ApplicationsProduct Engineering
About Sunset
We help tech companies shut down. From state withdrawals to liquidations, we save founders thousands of dollars, hundreds of hours, and countless headaches when it comes to winding down their operations.