Founding Backend Engineer, AI Agent Platform

RiseMe; Palo Alto (CA); Hybrid; USD 180,000 - 240,000; Full time

Benefits offered by this job

Hybrid in Palo Alto

Visa sponsorship available

Meals & perks: lunch, dinner, snacks,

Job summary

Goaly is building foundational AI systems and is hiring an engineer to join early on the harness between frontier models and real users. You will own the agent loop, sandbox environments, and the evaluation stack, shipping to customers and iterating based on production traces.

You will design context engineering, ensure observability and replayability, and balance cost, latency, and quality across model calls and tool use while working without a fixed playbook.

Qualifications

• 5+ years building production software and running systems at scale.
• Built and shipped an agentic system with tool use that real users depend on.
• Experience with failure modes: context overflow, agent looping, tool misuse, prompt injection, runaway cost.
• Strong Python and at least one of TypeScript, Go, or Rust; familiar with Linux and cloud infra.
• Ability to explain trade-offs clearly to engineers, researchers, and customers.
• Willingness to work without a playbook and move quickly with rigor.

Responsibilities

• Own the harness: the agent loop, tool interface, prompts, permissions, stop conditions, retries and budget caps.
• Build sandboxed execution environments (containers / microVMs) for thousands of rollouts in parallel.
• Design context engineering: what goes into the window, retrieval, state, and hand-offs between sub-agents.
• Make every agent run observable and replayable: trace model and tool calls and state changes.
• Build the eval stack: offline suites, production traces, and checks for failures.

Skills

Python

TypeScript

Go

Rust

Linux

Cloud infrastructure

Tools

Docker

Job description

Goaly is building foundational AI systems and is hiring an engineer to join early on the harness between frontier models and real users. You will own the agent loop, sandbox environments, and the evaluation stack, shipping to customers and iterating based on production traces.

You will design context engineering, ensure observability and replayability, and balance cost, latency, and quality across model calls and tool use while working without a fixed playbook.