Software Architect - Tracking

Global Sports Jobs Limited; United States; Remote; USD 180,000 - 240,000; Full time

Job summary

Hawk-Eye Innovations in the United States seeks a senior computer vision engineering authority for its tracking technology. This hands-on, individual contributor role combines software architecture ownership with expert CV leadership across camera calibration, ball and skeletal tracking, and real-time pipelines.

You will drive architecture across multiple squads and sports, evaluate new tracking approaches, and mentor engineers while collaborating with external partners such as Sony, NVIDIA and

Qualifications

• Deep multi-camera computer vision expertise.
• Camera calibration including intrinsics, extrinsics, distortion models, anti-wobble and bundle adjustment.
• Triangulation.
• 3D ball and pose estimation, skeletal tracking, continuous-time modelling and inverse kinematics.
• Expert cross-platform C++ across Windows and Linux, x86 and ARM, with CMake and real performance profiling ability.
• Strong working knowledge of GPU inference (TensorRT, Triton) and ML pipelines (PyTorch, ONNX).
• Proven experience running tracking at scale in AWS, on-premise and on edge devices.
• Hands-on use of AI coding agents and LLM orchestration to accelerate algorithm R&D and refactoring in large codebases.
• Working understanding of generative AI, synthetic data generation and where they genuinely help real-time CV.
• Ability to set architecture across many squads and sports and make pragmatic calls on reuse, cost and time to market.
• Ability to write clearly, including design documents, proposals with options, and explanations a non-technical stakeholder can follow.
• Comfortable working in front of external engineering partners, including Sony, NVIDIA and AWS alongside sports leagues and federations.
• Ability to size work honestly, state confidence in it, and say what should be stopped or delayed.

Responsibilities

• Lead architecture for every tracking and auto-officiating product in the Tracking and Automated Officiating value stream.
• Set initial architecture when a new tracking problem enters the business, run the Software Domain Owner model so shared libraries such as calibration have named codeowners, and keep designs consistent across sports.
• Represent tracking in the Engineering Architecture Steering group and contribute to architecture conversations across Hawk-Eye and the wider Sony Sports organisation.
• Make pragmatic judgements about reuse, including where a common tracking codebase pays off and where it does not.
• Act as subject matter authority for computer vision, deciding where vision processing and ML integration goes next.
• Research new tracking technologies, bring them in, and build prototypes when a proposal needs proving.
• Lead adoption of modern tooling, including agentic coding frameworks, LLM-driven development tools and automated code generation in heavy C++ and Python codebases, and decide what earns its place.
• Coach Squad Tech Leads, guide junior architects, run CV Algorithm talks, HawkTalks and tutorials, and help hire well including technical assessment for CV and ML roles.
• Own the operational health of ML training and synthetic data infrastructure, including escalating gaps in ownership and support with options attached.
• Serve as escalation point and get into the code when a live delivery is at risk.

Skills

Multi-camera CV

Camera calibration

Triangulation

Ball/pose estimation

Skeletal tracking

C++ expert

CMake

GPU inference

TensorRT

PyTorch

ONNX

LLM orchestration

Generative AI

Architecture leadership

Documentation

External collaboration

Tools

Windows

Linux

CUDA

Job description

About the Role

This is the senior computer vision engineering authority for Hawk-Eye's tracking technology, an individual contributor role. The role carries two hats: as Software Architect, owning software-level architectural design across tracking, auto-officiating and data delivery; and as computer vision authority, leading core domains including camera calibration, ball tracking, skeletal tracking and related R&D. The tracking technology underpins products such as goal-line technology, semi-automated offside, electronic line calling and automated ball-strike, across multiple sports and deployment environments. The role sits within the Tracking and Automated Officiating value stream, working alongside over 100 engineers, and is hands-on, including escalation into code when live delivery is at risk. It is not a people management, project or delivery management, Product Owner or Squad Tech Lead role; those responsibilities sit elsewhere.

Key Responsibilities

• Lead architecture for every tracking and auto-officiating product in the Tracking and Automated Officiating value stream.
• Set initial architecture when a new tracking problem enters the business, run the Software Domain Owner model so shared libraries such as calibration have named codeowners, and keep designs consistent across sports.
• Represent tracking in the Engineering Architecture Steering group and contribute to architecture conversations across Hawk-Eye and the wider Sony Sports organisation.
• Make pragmatic judgements about reuse, including where a common tracking codebase pays off and where it does not.
• Act as subject matter authority for computer vision, deciding where vision processing and ML integration goes next.
• Research new tracking technologies, bring them in, and build prototypes when a proposal needs proving.
• Lead adoption of modern tooling, including agentic coding frameworks, LLM-driven development tools and automated code generation in heavy C++ and Python codebases, and decide what earns its place.
• Coach Squad Tech Leads, guide junior architects, run CV Algorithm talks, HawkTalks and tutorials, and help hire well including technical assessment for CV and ML roles.
• Own the operational health of ML training and synthetic data infrastructure, including escalating gaps in ownership and support with options attached.
• Serve as escalation point and get into the code when a live delivery is at risk.

Required Experience & Qualifications

• Deep multi-camera computer vision expertise.
• Camera calibration including intrinsics, extrinsics, distortion models, anti-wobble and bundle adjustment.
• Triangulation.
• 3D ball and pose estimation, skeletal tracking, continuous-time modelling and inverse kinematics.
• Expert cross-platform C++ across Windows and Linux, x86 and ARM, with CMake and real performance profiling ability.
• Strong working knowledge of GPU inference (TensorRT, Triton) and ML pipelines (PyTorch, ONNX).
• Proven experience running tracking at scale in AWS, on-premise and on edge devices.
• Hands-on use of AI coding agents and LLM orchestration to accelerate algorithm R&D and refactoring in large codebases.
• Working understanding of generative AI, synthetic data generation and where they genuinely help real-time CV.
• Ability to set architecture across many squads and sports and make pragmatic calls on reuse, cost and time to market.
• Ability to write clearly, including design documents, proposals with options, and explanations a non-technical stakeholder can follow.
• Comfortable working in front of external engineering partners, including Sony, NVIDIA and AWS alongside sports leagues and federations.
• Ability to size work honestly, state confidence in it, and say what should be stopped or delayed.