ML Engineer, Inference & Optimization

Pika; United States; Remote; USD 180,000 - 260,000; Full time

Benefits offered by this job

Competitive salary

Equity

Health benefits

Collaborative culture

Job summary

Pika, a Palo Alto–based AI startup, is seeking Senior/Staff Inference Engineers to accelerate AI-driven products. You will design and optimize inference pipelines, implement state‑of‑the‑art acceleration techniques, and collaborate with researchers to push real-time video and language models to production.

You’ll maximize GPU parallelism using CUDA and NCCL, develop high‑performance kernels, and contribute to model deployment and training efficiency.

Qualifications

• 5+ years engineering experience in inference acceleration and deployment at scale.
• Expertise in inference optimization, quantization, and attention acceleration.
• Strong GPU programming experience with CUDA and NCCL.
• Familiarity with videogen models and large language models.
• Excellent cross-discipline collaboration and ownership mindset.

Responsibilities

• Accelerate inference using advanced acceleration techniques.
• Maximize GPU parallelism across tensor, sequence, and pipeline parallelism.
• Develop high-performance kernels and distributed workloads with CUDA/NCCL.
• Advance AI deployment of videogen and LLMs into production.
• Improve training efficiency and participate in code reviews.

Skills

Inference acceleration

GPU programming

CUDA

NCCL

Distributed inference

Quantization

Model deployment

Collaboration

Tools

CUDA

NCCL

Job description

About the Role

We are seeking Senior/Staff level Inference Engineers to accelerate the performance of Pika's AI-driven products. In this highly technical role, you will operate at the intersection of cutting-edge inference acceleration, GPU parallelism, advanced model deployment, and video generation technologies. Your expertise will drive significant improvements to model speed and efficiency, ensuring our creative AI systems deliver industry-leading user experiences at scale.

You will design and optimize inference pipelines, implement state-of-the-art acceleration techniques, and work closely with researchers and engineers across the team to push the boundaries of what’s possible in real-time AI deployment. Your efforts will play a foundational role in powering the next generation of Pika’s video and language models.

What You’ll Do

• Accelerate Inference: Lead and implement advanced inference acceleration techniques, including attention optimization and quantization for efficient model serving.

• Maximize GPU Parallelism: Engineer and optimize GPU strategies across tensor, sequence, and pipeline parallelism (TP, SP, PP) for maximal efficiency and scalability.

• Programming for Performance: Develop and optimize high-performance computing kernels and distributed workloads using CUDA and NCCL.

• Advance AI Deployment: Collaborate with research and engineering teams to bring state-of-the-art videogen and large language models into production.

• Improve Training Efficiency: (Bonus) Contribute to improvements in model training speed, stability, and resource utilization as part of our deployment lifecycle.

• Technical Excellence: Drive rigorous code reviews, participate in technical discussions, and mentor fellow engineers on best practices in inference and GPU programming.

What We’re Looking For

• Experience: 5+ years engineering experience, with a strong track record in inference acceleration and model deployment at scale.

• Inference Mastery: Proven expertise in inference optimization, including quantization, attention acceleration, and deep learning compiler stacks.

• GPU & Parallelism: Deep knowledge of GPU programming (CUDA, NCCL) and experience with SP, TP, PP, and other forms of parallelism for distributed inference.

• AI Domain Knowledge: Familiarity with video generation (videogen) models and large language models (LLMs).

• Collaboration: Strong cross-discipline communication skills; able to drive shared goals across research and engineering functions.

• Ownership Mindset: Self-driven, solutions-oriented, and capable of managing ambiguity in a fast-paced startup environment.

• Bonus: Experience in enhancing training efficiency, stability, or resource optimization for large models.

Nice to Have

• Experience with high-throughput video or real-time streaming model deployment

• Familiarity with distributed training and optimization toolkits

• Contributions to open source projects in AI infrastructure or deep learning compilers

• Startup or rapid prototyping experience

What We Offer

• Competitive salary in the AI industry

• Equity in a fast-growing startup shaping the future of AI

• Comprehensive health benefits, monthly stipends, company retreats

• A supportive and collaborative office culture—we’re all building and launching together

About Pika

At Pika, we're crafting a future where video creation is seamless, intuitive, and universally accessible. Our mission is to empower creativity by breaking down technical barriers using the transformative power of AI. We’re a tight-knit, energetic team based in Palo Alto, CA, valuing efficiency, curiosity, and the ambition to make a meaningful impact on the world.

We work from our Palo Alto office 3-5 days a week and welcome applicants who are eager to contribute onsite.

This is a remote role. Applicants must be located in: United States.