Software Engineer, Platform & Infrastructure - DeepFrame Engineering — San Francisco / Palo Alto, CA English (required); Japanese a plus, not required View role

About this role

Software Engineer, Platform & Infrastructure - DeepFrame

You will build and run the infrastructure behind our video platform, shipping it with engineers across our team.

Back to Careers

Location : San Francisco / Palo Alto, CA

Employment type : Full-time

Location type : Hybrid

Department : Engineering

Apply Now

Learn more about InfiniMind

About the role

You will build and run the GPU inference, video-processing, ingestion, indexing, and search infrastructure behind the platform, and ship it with engineers across our team. You will own reliability and observability, join customer technical meetings, and help get customer video onto the platform.

What you'll do

• Build and run GPU inference and video-processing infrastructure on AWS
• Scale ingestion and indexing pipelines for large video libraries
• Work on the search and retrieval layer and the APIs customers integrate with
• Build connectors to customer video sources (S3, cloud storage, video archives) and result destinations (APIs, webhooks)
• Own reliability and observability, and join customer technical meetings to help get customer video onto the platform

Who thrives here

• 5+ years building production infrastructure or backend platforms, with real distributed-systems depth
• Strong Python, plus Go, Rust, or C++
• GPU workloads in production, for example CUDA, TensorRT, or Triton
• Large data or media pipelines run reliably
• Can explain technical tradeoffs to a customer's engineers

Nice to have

• AWS, containers, and Kubernetes
• Video processing, vector search, ML serving, or enterprise deployment

Your first 3 months

• Learn the ingestion, indexing, and search layers and the codebase you will ship into
• Join customer technical meetings and help get customer video onto the platform
• Take ownership of reliability and observability for the inference and video-processing services

By 6 months

• Build connectors to customer video sources, such as S3, cloud storage, or video archives
• Scale ingestion and indexing pipelines for large video libraries
• Work on the search and retrieval layer and the APIs that customers integrate with

Backgrounds that could fit

• Backend or platform engineer who has run production services at scale
• ML infrastructure or model-serving engineer
• Computer vision or video-processing engineer who has worked on large media pipelines
• Search or retrieval engineer who has shipped APIs that customers integrate with
• Infrastructure engineer who has run GPU workloads in production

Location

In person in San Francisco or Palo Alto at least 3 days a week, with some customer travel. Based in the Bay Area, or willing to relocate before your start date.

To apply

Email your resume or LinkedIn profile and a short note or link on a system you built to [email removed].

Equal opportunity

InfiniMind Inc. is an equal opportunity employer. We consider qualified applicants regardless of race, color, religion, sex, pregnancy, sexual orientation, gender identity or expression, marital status, national origin, ancestry, disability, medical condition, genetic information, veteran or military status, age, or any other characteristic protected by applicable law. We consider qualified applicants with criminal histories in a manner consistent with the California Fair Chance Act. We provide reasonable accommodations during the hiring process; to request one, email [email removed]. You must be authorized to work in the United States without employer sponsorship, now or in the future.

How we hire

From first conversation to offer, we keep the process short.

1. 01

Casual conversation

Email your resume or LinkedIn profile and a short note. We then hold a 30-minute conversation about the role and what you'd be working on.

1. 02

Technical interview

A walkthrough of your past work. No take-home assignment.

1. 03

Founder conversation and offer

A direct conversation with the founders, followed by reference checks and an offer.