Senior Real-Time Multimodal Inference Architect

Amazon

Sunnyvale (CA)

On-site

USD 192,000 - 260,000

Full time

6 days ago
Be an early applicant

Get more replies from employers

Send a job-specific resume in minutes.

Benefits offered by this job

Health insurance
401(k) matching
RSU/Stock options

Job summary

Amazon is seeking a Senior Inference Engineer in Sunnyvale, CA to own the end-to-end inference stack for real-time multimodal conversational AI. You will shape model architectures, build low-latency streaming serving paths, and develop offline training and RL/evaluation infrastructure.

Expect cross-team collaboration with scientists and hardware partners to ensure scalable, cost-effective performance. You will drive architecture co-design, optimize large-scale inference, and implement

Qualifications

  • 3+ years building ML models for business applications
  • PhD or MS + 6+ years research experience
  • Experience programming in Java, C++, Python or related language
  • 2+ years optimizing inference for neural models
  • Strong understanding of transformers and autoregressive decoding
  • Production latency-constrained inference experience

Responsibilities

  • Own end-to-end inference stack from research to production
  • Optimize real-time streaming inference for multimodal models
  • Implement low-latency serving paths and multi-GPU inference
  • Develop offline training and RL evaluation infrastructure

Skills

Machine learning inference
Java/C++/Python
Latency optimization
Profiling
Multimodal models
Real-time systems
Ocean of compute

Education

PhD or MS + 6+ yrs research

Tools

Nsight Compute
PyTorch
TensorRT

Job description

Amazon is seeking a Senior Inference Engineer in Sunnyvale, CA to own the end-to-end inference stack for real-time multimodal conversational AI. You will shape model architectures, build low-latency streaming serving paths, and develop offline training and RL/evaluation infrastructure.

Expect cross-team collaboration with scientists and hardware partners to ensure scalable, cost-effective performance. You will drive architecture co-design, optimize large-scale inference, and implement

Get your free, confidential resume review.
or drag and drop your file here.
Similar jobs

Similar jobs worth comparing

Senior Real-Time Multimodal Inference Engineer
Senior Real-Time Multimodal Inference Engineer

Amazon • Boston (MA), Northern (KY)

Hybrid
USD 167,000 - 226,000
Senior Real-Time Multimodal AI Scientist
Senior Real-Time Multimodal AI Scientist

Amazon Science • Sunnyvale (CA)

On-site
USD 192,000 - 260,000
Lead Real-Time Multimodal AI Scientist
Lead Real-Time Multimodal AI Scientist

Amazon • Sunnyvale (CA)

On-site
USD 229,000 - 309,000
Realtime Multimodal Inference Architect
Realtime Multimodal Inference Architect

techire.® • San Francisco (CA)

On-site
USD 140,000 - 210,000
Medical insurance (including dental &视
Dental insurance
Vision insurance
+4
Senior Applied Scientist, Real-Time Multimodal AI
Senior Applied Scientist, Real-Time Multimodal AI

Amazon • Seattle (WA)

On-site
USD 167,000 - 226,000
Lead Real-Time Multimodal AI Scientist, Conversational/AGI
Lead Real-Time Multimodal AI Scientist, Conversational/AGI

Amazon • Bellevue (WA)

On-site
USD 180,000 - 260,000
Senior Inference Engineer, AGI
Senior Inference Engineer, AGI

Amazon • Sunnyvale (CA)

On-site
USD 192,000 - 260,000
Health insurance
401(k) matching
RSU/Stock options
Senior Inference Engineer, AGI
Senior Inference Engineer, AGI

Amazon • Boston (MA), Northern (KY)

On-site
USD 167,000 - 226,000
Senior AI Infra Engineer — Real-Time Multimodal Inference
Senior AI Infra Engineer — Real-Time Multimodal Inference

Ambient AI, Inc. • Redwood City (CA)

Hybrid
USD 190,000 - 270,000
Stock options
Health, dental, vision
401(k)
+1
Senior Real-Time Conversational AI Scientist (AGI)
Senior Real-Time Conversational AI Scientist (AGI)

Amazon • Boston (MA)

On-site
USD 167,000 - 226,000
Health insurance
401(k) matching
Paid time off
+1