Cognitiv
Senior Software Engineer, ML Inference
–
Cognitiv
Location:
Hybrid – MTW out of our Bellevue, WA office.
Overview At Cognitiv, we are redefining media buying with our Deep Learning Advertising Platform. We harness cutting‑edge deep learning technology and data science to bring intelligence to advertising and deliver precision, relevance, and impact at scale.
What You’ll Do
Build and optimize ML inference systems used in production, leveraging industry‑standard frameworks and in‑house technology.
Implement performance‑critical components in C++ and PyTorch/LibTorch focused on latency, throughput, and reliability.
Collaborate with ML Research, Product, and Engineering partners to bring models from experimentation into production.
Improve existing systems by identifying performance bottlenecks, reliability gaps, and scalability issues.
Contribute to design discussions and technical reviews for inference‑related services.
Write high‑quality, production‑ready code with strong testing, monitoring, and documentation.
Support the full development lifecycle of services you work on, from design through deployment and iteration.
Mentor teammates through code reviews and knowledge sharing.
Tech Stack
PyTorch / LibTorch
C++17 or later
Managed languages: C#, Java
Cloud platforms: AWS, GCP, or Azure
ML optimization techniques: parallelism, quantization, tiling, etc.
Modern ML inference tooling: ExecuTorch, etc.
Who You Are
4+ years of experience building ML systems in production, hands‑on with PyTorch or LibTorch.
4+ years professional C++ experience focusing on performance and memory efficiency.
Experience optimizing models and inference pipelines for latency and scale.
Collaborative communicator able to explain trade‑offs to cross‑functional partners.
Ownership‑driven, takes responsibility for building and improving services over time.
Bachelor’s degree or higher in Computer Science, Engineering, Math, Physics, or related field.
Bonus Points If You Have
GPU or hardware‑accelerated inference (NVIDIA TensorRT, etc.)
Docker and Kubernetes experience
Infrastructure‑as‑Code tools (Terraform, Ansible)
Advanced ML architectures (two‑tower models, teacher‑student learning)
Rust experience
MLOps tooling (monitoring, lifecycle management, automation)
AI‑assisted development tools
Salary & Benefits Salary:
$160,000 - $210,000 USD Base Salary + Equity
Medical, dental & vision coverage (some plans 100% employer‑paid)
12 weeks paid parental leave
Unlimited PTO + Work‑From‑Anywhere August
Career development with clear advancement paths
Equity for all employees
Hybrid work model & daily team lunch
Health & wellness stipend + cell phone reimbursement
401(k) with employer match
Parking (CA & WA offices) & pre‑tax commuter benefits
Employee Assistance Program
Comprehensive onboarding (Cognitiv University)
Cognitiv is proud to be an equal‑opportunity employer. We celebrate diversity and are committed to creating an inclusive workplace for all.
#J-18808-Ljbffr
–
Cognitiv
Location:
Hybrid – MTW out of our Bellevue, WA office.
Overview At Cognitiv, we are redefining media buying with our Deep Learning Advertising Platform. We harness cutting‑edge deep learning technology and data science to bring intelligence to advertising and deliver precision, relevance, and impact at scale.
What You’ll Do
Build and optimize ML inference systems used in production, leveraging industry‑standard frameworks and in‑house technology.
Implement performance‑critical components in C++ and PyTorch/LibTorch focused on latency, throughput, and reliability.
Collaborate with ML Research, Product, and Engineering partners to bring models from experimentation into production.
Improve existing systems by identifying performance bottlenecks, reliability gaps, and scalability issues.
Contribute to design discussions and technical reviews for inference‑related services.
Write high‑quality, production‑ready code with strong testing, monitoring, and documentation.
Support the full development lifecycle of services you work on, from design through deployment and iteration.
Mentor teammates through code reviews and knowledge sharing.
Tech Stack
PyTorch / LibTorch
C++17 or later
Managed languages: C#, Java
Cloud platforms: AWS, GCP, or Azure
ML optimization techniques: parallelism, quantization, tiling, etc.
Modern ML inference tooling: ExecuTorch, etc.
Who You Are
4+ years of experience building ML systems in production, hands‑on with PyTorch or LibTorch.
4+ years professional C++ experience focusing on performance and memory efficiency.
Experience optimizing models and inference pipelines for latency and scale.
Collaborative communicator able to explain trade‑offs to cross‑functional partners.
Ownership‑driven, takes responsibility for building and improving services over time.
Bachelor’s degree or higher in Computer Science, Engineering, Math, Physics, or related field.
Bonus Points If You Have
GPU or hardware‑accelerated inference (NVIDIA TensorRT, etc.)
Docker and Kubernetes experience
Infrastructure‑as‑Code tools (Terraform, Ansible)
Advanced ML architectures (two‑tower models, teacher‑student learning)
Rust experience
MLOps tooling (monitoring, lifecycle management, automation)
AI‑assisted development tools
Salary & Benefits Salary:
$160,000 - $210,000 USD Base Salary + Equity
Medical, dental & vision coverage (some plans 100% employer‑paid)
12 weeks paid parental leave
Unlimited PTO + Work‑From‑Anywhere August
Career development with clear advancement paths
Equity for all employees
Hybrid work model & daily team lunch
Health & wellness stipend + cell phone reimbursement
401(k) with employer match
Parking (CA & WA offices) & pre‑tax commuter benefits
Employee Assistance Program
Comprehensive onboarding (Cognitiv University)
Cognitiv is proud to be an equal‑opportunity employer. We celebrate diversity and are committed to creating an inclusive workplace for all.
#J-18808-Ljbffr