Salt AI

• Workflow and agent execution. Build the contracts that let agents call real pipelines with typed inputs, structured outputs, streaming status, retries, logs, and auditability. • Python and Django platform services. Model platform concepts cleanly, build durable APIs, evolve service boundaries, and make customer workflows reliable at the backend layer. • Kubernetes-backed execution. Work on deployment patterns, scaling, isolation, runtime behavior, observability, and operational reliability for AI workflows. • Fullstack platform surfaces. Build the frontend and backend experiences customers use to configure, run, inspect, debug, and reuse AI workflows. • Permission-aware data access. Build secure customer data access patterns, retrieval systems, indexing, hybrid search, and APIs that respect enterprise boundaries. • Reliability and observability. Make distributed AI workflows understandable: what ran, what changed, what failed, why it failed, and what the user or system can do next. • Platform abstractions. Turn one-off customer implementations into reusable capabilities without sanding off the important domain-specific details. • Developer and operator experience. Improve the tools, docs, test harnesses, internal workflows, and diagnostics that let a small team move quickly without losing control of the system. This is not a pure infrastructure role. The right person can move through the stack, find the real constraint, and leave the customer experience better shaped than they found it.

• Create beautiful, deeply usable interfaces for complex workflows • Build experiences where users can run, guide, inspect, approve, and recover AI workflows without losing trust in what the system is doing • Create interaction patterns for approvals, parameter review, result inspection, exception handling, and other moments where users need to make load-bearing decisions • Make distributed AI workflows understandable: what ran, what changed, what failed, why it failed, and what the user or system can do next • Help Salt feel like one product instead of disconnected surfaces • Work across React, TypeScript, APIs, backend services, and platform contracts to configure, run, inspect, debug, and reuse AI workflows • Build interfaces for permission-aware search, indexed customer data, result inspection, citations, confidence, and trust • Turn complex backend capabilities into product primitives customers and internal teams can safely build on