Cognitiv · 1 day ago
Senior Staff Software Engineer, ML Inference
Cognitiv is an innovative AdTech company revolutionizing the advertising industry with its Deep Learning Advertising Platform. They are seeking a Senior Staff Software Engineer specializing in ML Inference to architect and scale a cutting-edge inference system that will be integral to their ML-driven products, while also leading cross-organizational initiatives and mentoring other engineers.
AdvertisingAnalyticsArtificial Intelligence (AI)Big DataMachine Learning
Responsibilities
Build and Optimize Inference Systems: Implement and optimize large-scale ML inference systems using both industry-standard frameworks and in-house technologies
Lead Cross-Team Technical Initiatives: Drive major organization-wide technical programs that advance Cognitiv’s ML inference capabilities
Evaluate and Advance ML Breakthroughs: Identify emerging ML inference technologies and partner with Product to build business cases for new capabilities
Deliver Production-Grade ML Solutions: Collaborate with Engineering, Research, and Product to design and integrate high-performing ML solutions into production systems
Raise the Engineering Bar: Mentor engineers through code reviews, design reviews, and pair programming to elevate technical quality
Set Engineering Standards: Define and automate best-in-class standards for coding, testing, observability, and security across inference systems
Own the Full Development Lifecycle: Take end-to-end ownership of services including planning, design, execution, testing, and release
Qualification
Required
4+ years of experience with modern PyTorch/LibTorch and awareness of the latest ecosystem innovations
4+ years optimizing models through quantization, parallelism, tiling, and related techniques
4+ years programming in C++17 or later, with deep knowledge of performance and memory considerations
Able to shape organization-wide technical narratives and drive alignment across teams
Comfortable owning services through the full development lifecycle, from design to release
Bachelor's or advanced degree in Computer Science, Engineering, Math, Physics, or a related field
Preferred
Experience with GPU/hardware acceleration for inference (e.g., NVIDIA TensorRT)
Experience with containers (Docker, Kubernetes)
Familiarity with Infrastructure-as-Code (Terraform, Ansible)
Experience with advanced ML architectures (two-tower models, teacher-student learning)
Experience with Rust
Experience with MLOps systems (monitoring, lifecycle management, automation)
Experience using AI-driven development tools (AI code assistants, AI code review)
Benefits
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)
…and more!
Company
Cognitiv
Cognitiv uses proprietary Deep Learning technology to help companies with Big Data problems get beyond analysis to decisions.
H1B Sponsorship
Cognitiv has a track record of offering H1B sponsorships. Please note that this does not
guarantee sponsorship for this specific role. Below presents additional info for your
reference. (Data Powered by US Department of Labor)
Distribution of Different Job Fields Receiving Sponsorship
Represents job field similar to this job
Trends of Total Sponsorships
2025 (6)
2024 (10)
2023 (3)
2022 (1)
2021 (10)
Funding
Current Stage
Growth StageTotal Funding
$4.95M2019-03-07Convertible Note· $0.45M
2018-03-01Seed
2017-12-15Convertible Note· $1.7M
Recent News
2026-01-06
2026-01-06
Company data provided by crunchbase