Software Engineer, Control Plane; Senior​/Principal

About Positron AI

Positron AI specializes in developing custom hardware systems to accelerate AI inference. These inference systems offer significant performance and efficiency gains over traditional GPU-based systems, delivering advantages in both performance per dollar and performance per watt. Positron AI exists to create the world's best AI inference systems.

We are looking for a Senior or Principal Software Engineer to contribute to control-plane architecture and hands‑on development for Positron AI inference systems. You will write software that connects low‑level hardware capabilities to system management, diagnostics, security, and firmware updates. Go is our primary implementation language, with C, C++, Python, Bash, and other languages used where they fit the system boundary.

This role can fit a senior/principal software engineer or systems architect who remains a strong, current coder and wants ownership grounded in production implementation. You will set technical direction, define stable secure interfaces, and write, review, profile, and debug production code alongside the team.

The scope spans a wide swath of the platform. You will own substantial features end to end, from problem definition and architecture through implementation, integration, testing, and production validation.

Platform Architecture and Implementation

• Contribute to the architecture and evolution of the system management services and APIs that control hardware state, resources, diagnostics, updates, and workloads.
• Design, write, and review production Go, reaching for C, C++, Python, or Bash at the boundaries where they are the right tools.
• Work across the full stack, from web applications and management APIs through Linux services, hardware interfaces, and low‑level protocols.
• Refactor critical subsystems to improve modularity, testability, and fault isolation, and to support future hardware generations.
• Define stable interfaces and data models for orchestration, diagnostics, management tooling, and customer‑facing workflows.

Hardware and System Integration

• Partner with internal and external hardware, firmware, and systems engineers to turn low‑level capabilities into reliable platform services.
• Debug failures at the board and system level across CPU, memory, drives, USB, I2C, SMBus, PCIe, and in‑system accelerators, including FPGAs.
• Build safe control paths for reboot state, accelerator reset and recovery, hardware health, and resource allocation.
• Integrate management‑controller capabilities, hardware counters, and telemetry into platform APIs and operational workflows.

Diagnostics, Observability, and Reliability

• Expose diagnostics through platform APIs with persistent results, searchable reporting, and periodic archiving.
• Build comprehensive metrics, logs, and alerts with configurable sinks, including Open Telemetry‑compatible systems.
• Integrate external health probes so failed hardware or workloads can be isolated, rescheduled, and recovered safely.
• Profile system behavior, diagnose performance regressions, and drive root causes through to resolution.

Security and Software Lifecycle

• Implement certificate management, role‑based access control, pluggable authentication, and integrations with HSM‑backed secret stores.
• Build secure boot, signed‑artifact, software and firmware update, and rollback workflows.
• Secure model acquisition and side loading with appropriate authentication, secret management, and status reporting.

Technical Leadership and Engineering Practices

• Translate product and hardware roadmaps into software architecture, sequenced execution plans, and clear technical decisions.
• Lead design and code reviews across software, firmware,…