Senior Software Engineer, AI Platform

Ridgeline•Reno, NV

3h•$153,000 - $210,000•Hybrid

About The Position

Are you a skilled software engineer looking to build agentic AI systems and ship them in production? Do you want to help shape how autonomous, tool-using AI agents get built into a real, customer-facing product? If so, we invite you to apply to join our AI Platform team, where we're building the future of investment management software. As a Senior Software Engineer on the AI Platform team, you'll build and ship features across Ridgeline's agentic AI platform, the foundational AI infrastructure that powers AI capabilities across the company. You'll work alongside the engineers who built it from the ground up. Together, you'll take on some of the most interesting problems in applied AI, including agent memory, and how models reason, call tools, and collaborate with one another, all as part of a tight-knit team whose work reaches across the entire company.

Requirements

4+ years of professional software engineering experience building and shipping production applications.
Proficiency in a statically typed language such as Kotlin or TypeScript; full-stack experience (including React) is a plus.
Comfort using AI coding tools as part of your everyday development workflow.
Strong collaboration and communication skills, with the ability to work closely across multiple partner teams in a fast-moving environment.
Ability to ramp up quickly in a new codebase and deliver independently.
Familiarity with platform or service-oriented engineering practices.

Nice To Haves

Experience building and shipping AI-powered products in production, including agentic workflows, tool calling, or RAG.
Experience working with Anthropic and/or OpenAI models and APIs.
Experience with MCP (Model Context Protocol) or similar tool-integration frameworks.
Background or interest in financial services or investment management.

Responsibilities

Build and ship features across the AI platform, including agent builder capabilities, agent memory, cost guardrails, and expanded tool integrations.
Implement and improve retrieval-augmented generation (RAG) workflows and integrations with external data sources, including via Model Context Protocol (MCP).
Contribute to model efficiency work such as code execution and model routing to optimize token usage and cost.
Partner closely and regularly with cross-functional teams - including other AI teams, product teams, platform teams, and security - to extend AI capabilities across the company.
Use AI-assisted development tools as a core part of your daily workflow.
Collaborate closely with teammates through code review, knowledge-sharing, and solving problems together.