Cognichip · 10 hours ago
Staff LLMOps Engineer
United States
Full-time
Remote
Senior Level, Lead/Staff
$100K/yr - $300K/yr
5+ years expCognichip is building the next generation, enterprise product suite to empower semiconductor design engineers with AI/ML models. They are seeking a Staff LLMOps Engineer to architect, deploy, and optimize large language model infrastructure on the cloud, focusing on production deployment and scaling across GPU clusters.
AI InfrastructureArtificial Intelligence (AI)ManufacturingSemiconductor
Responsibilities
Design and implement production-ready LLM deployment pipelines on AWS and Kubernetes/EKS
Build and scale LLM inference infrastructure (multi-GPU, multi-node) for high availability, low latency, and cost efficiency
Optimize inference performance using vLLM, SGLang, or similar frameworks
Implement advanced serving techniques: continuous batching, speculative decoding, KV-cache management, paged attention, and distributed scheduling
Collaborate with AI researchers to operationalize model training outputs into production-grade services
Establish monitoring and observability for LLM serving: latency, throughput, GPU utilization, failure recovery
Drive automation of infrastructure provisioning, scaling, and updates using IaC (Terraform) and CI/CD pipelines
Partner with security and compliance teams to ensure secure multi-tenant model hosting aligned with enterprise-grade requirements
Qualification
Required
5+ years of experience in DevOps/AI infrastructure, with 2+ years focused on LLMOps (production deployment & optimization)
Proven track record of deploying and scaling LLMs in production environments
Hands-on experience with GPU-accelerated inference and distributed AI serving
Strong understanding of cloud-native architectures and secure enterprise SaaS deployment
Benefits
Competitive compensation package, including equity participation.
Company
Cognichip
Cognichip is an AI-first deep tech company focused on transforming the semiconductor industry by revolutionizing how chips are designed.
51-200 employees
H1B Sponsorship
Cognichip 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 (5)
Funding
Current Stage
Growth StageTotal Funding
$33M2025-05-15Seed· $33M
Leadership Team
Faraj Aalaei
Founder & Chief Executive Officer
Ehsan Kamalinejad
Co-Founder & CTO
Recent News
2026-01-22
Company data provided by crunchbase