Software Engineer - Agent Infra
USD 200,000-300,000 per year
SCRAPED
Used Tools & Technologies
Not specified
Required Skills & Competences ?
Security @ 3 Go @ 6 Python @ 6 Java @ 6 API @ 3Details
Perplexity is an AI-powered answer engine founded in December 2022 and growing rapidly as one of the worldβs leading AI platforms. Perplexity has raised over $1B in venture investment and aims to build accurate, trustworthy AI that powers decision-making and assistive AI. The role focuses on building the core infrastructure that powers agentic products across Perplexity, including Search, Deep Research, and the Comet browser.
Responsibilities
- Design and implement a highly reliable and scalable agent runtime: orchestration, shared state and memory, tool calling interfaces, and scheduling for cost, latency, and quality.
- Build secure sandboxed execution for agent actions and code; optimize cold start, isolation, and observability.
- Ship unified interfaces for multiple model sizes and providers. Integrate with open tool ecosystems such as MCP-style connectors for data and actions.
- Develop an evaluation platform for online and offline assessments, A/B tests, safety checks, and regression gates to improve agent reliability over time.
- Partner with Research, Inference, and Search to land 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. Familiar with metrics, tracing, on-call, and incident practices.
- Bias to own problems across layers, collaborate in fast moving teams, and ship.
Nice to have
- Prior work on agent orchestration pipelines: 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.
Compensation & Benefits
- Cash compensation range: $200,000 - $300,000 per year. Final offers determined by experience and expertise.
- Equity may be part of the total compensation package.
- Comprehensive health, dental, and vision insurance for you and your dependents. Includes a 401(k) plan.