Simplify Logo

Full-Time

Senior – Generative AI Deployment Engineer

San Jose

Posted on 2/10/2024

Recogni

Recogni

51-200 employees

High-performance AI inference for real-time object recognition

Automotive & Transportation
Hardware
AI & Machine Learning

Senior

San Jose, CA, USA

Category
Applied Machine Learning
AI Research
AI & Machine Learning
Required Skills
Python
Requirements
  • 3+ years of relevant software engineering experience
  • Proficiency in C++, Python, and modern machine learning frameworks
  • Experience in optimizing and deploying machine learning models, preferably LLMs for efficient inference
  • Good understanding of and ideally experience with high-performance distributed computing
  • Familiarity with hardware accelerators (GPUs, TPUs)
  • Experience with open-source compiler technologies such as TVM, XLA, MLIR, or LLVM
  • Equal opportunity employer
Responsibilities
  • Contribute to the design and implementation of the software stack for AI inference hardware
  • Participate in the co-design of hardware and software stack, particularly in the area of parallelizing AI models
  • Collaborate closely with machine learning engineers to identify the requirements of future machine learning workloads
  • Benchmark, analyze, and optimize the performance of key software components of the AI deployment software stack

Recogni specializes in high-performance, low-power AI inference solutions, offering the world's first Peta-Op class inference solution for real-time object recognition, enabling superhuman object detection accuracy up to 1000m and providing the industry's lowest latency and highest power efficiency. The company's technology allows for processing high-resolution camera data in real-time, enabling self-driving cars to navigate without human intervention under any condition.

Company Stage

Series C

Total Funding

$233.1M

Headquarters

San Jose, California

Founded

2017

Growth & Insights
Headcount

6 month growth

21%

1 year growth

29%

2 year growth

56%
INACTIVE