Software Engineer - Agent Infra (AI)

TL;DR

Senior Software Engineer (AI): Building and optimizing core infrastructure that powers agentic products across hirify.global, including Search, Deep Research, and the Comet browser with an accent on runtime, orchestration, evaluation, and training systems. Focus on designing highly reliable and scalable agent runtimes, secure sandboxed execution, and unified interfaces for multiple model providers.

Location: San Francisco, Palo Alto, New York City (USA)

Salary: $200K – $300K

Company

hirify.global is an AI company building agentic products like Search, Deep Research, and the Comet browser.

What you will do

• Design and implement a highly reliable and scalable agent runtime, covering orchestration, shared state, memory, tool calling interfaces, and scheduling.
• Build secure sandboxed execution environments for agent actions and code, optimizing cold start, isolation, and observability.
• Ship unified interfaces for multiple model sizes and providers, integrating with open tool ecosystems such as MCP style connectors.
• Develop an evaluation platform for online and offline assessments, A/B tests, safety checks, and regression gates to improve agent reliability.
• Partner with Research, Inference, and Search teams to deliver new agent capabilities end to end, from prototype to production.

Requirements

• 6+ years of industry experience building large scale systems or platforms.
• Experience building agent applications with tool calling, context engineering, or open connector integrations.
• Strong coding skills in one or more of: Python, Java, Go; comfortable with service design, APIs, and data models for high throughput systems.
• Working knowledge of containers, virtualization, and sandboxing.
• Familiarity with metrics, tracing, on call, and incident practices.

Nice to have

• Prior work on agent orchestration pipelines, including task routing, planning, memory graphs, vector search, or browser automation.
• Experience with evaluations, preference optimization, or RL to improve agent reliability.
• Exposure to MCP or similar open protocols for tool and data connectivity.
• Security hardening for multi-tenant workloads, snapshotting, or untrusted code execution.

Culture & Benefits

• Comprehensive benefits program for full-time U.S. employees, including equity, health, dental, vision, retirement, fitness, commuter, and dependent care accounts.
• Comprehensive benefits program for full-time employees outside the U.S. tailored to their region of residence.
• Bias to own problems across layers, collaborate in fast-moving teams, and ship.