FREE ACCESS
5,000–10,000 jobs/day
See all jobs on Scoutfield
Search thousands of fresh jobs every day.
Discover
- Fresh listings
- Fast filters
- No subscription required
Create a free account and start exploring right away.
Core Competencies
Role fitCore Competencies
Use this summary to align your resume positioning with the role.
Demonstrates expertise in designing and optimizing inference pipelines, implementing advanced inference acceleration techniques, and GPU programming with CUDA and NCCL. Proven ability to enhance model training efficiency and collaborate effectively across teams in a fast-paced environment.
Highest-signal resume keywords
Inference AccelerationGPU Programming with CUDAModel Deployment at ScaleAttention OptimizationQuantization
ATS Keywords
Tailor your resumeApplicant Tracking System Keywords
Tip: use these terms in your resume and cover letter to boost ATS matches.
Hard Skills
Inference OptimizationDeep Learning Compiler StacksHigh-Performance Computing KernelsDistributed WorkloadsTensor ParallelismSequence ParallelismPipeline ParallelismModel Training Speed ImprovementResource Utilization OptimizationVideo Generation Models
Soft Skills
Cross-Discipline CommunicationMentoringManaging Ambiguity
Tools & Technologies
NCCLCUDA
Industry Keywords
AI-Driven Video ProductsLarge Language ModelsReal-Time StreamingDistributed TrainingOpen Source AI Infrastructure
Tech Stack
Tools & technologiesOpen Source
About the role
Key responsibilities & impact- Design and optimize inference pipelines
- Implement advanced inference acceleration techniques, including attention optimization and quantization
- Engineer and optimize GPU strategies across tensor, sequence, and pipeline parallelism
- Develop and optimize high-performance computing kernels and distributed workloads using CUDA and NCCL
- Collaborate with research and engineering teams to bring video-generation and large language models into production
- Contribute to improvements in model training speed, stability, and resource utilization
- Drive rigorous code reviews and participate in technical discussions
- Mentor fellow engineers on inference and GPU programming best practices
- Accelerate Pika's AI-driven video and language products for real-time, scalable deployment
Requirements
What you’ll need- Senior/Staff level inference engineering experience
- 5+ years of engineering experience
- Strong track record in inference acceleration and model deployment at scale
- Expertise in inference optimization, including quantization, attention acceleration, and deep learning compiler stacks
- Deep knowledge of GPU programming with CUDA and NCCL
- Experience with sequence, tensor, pipeline, and other parallelism for distributed inference
- Familiarity with video generation models and large language models
- Strong cross-discipline communication skills
- Ability to manage ambiguity in a fast-paced startup environment
- Experience enhancing training efficiency, stability, or resource optimization for large models is a bonus
- Experience with high-throughput video or real-time streaming model deployment is nice to have
- Familiarity with distributed training and optimization toolkits is nice to have
- Contributions to open source AI infrastructure or deep learning compilers are nice to have
- Startup or rapid prototyping experience is nice to have
- Ability to regularly work from Pika's Palo Alto HQ
- Authorization to work for any employer in the United States and ability to answer US employment sponsorship questions
Benefits
Comp & perks- Equity in a fast-growing startup shaping the future of AI
- Comprehensive health benefits
- Monthly stipends
- Company retreats
- Supportive and collaborative office culture