Senior ML Engineer — Realtime Inference at Scale

BITKRAFT Ventures; Mountain View (CA); On-site; USD 270,000 - 500,000; Full time

Benefits offered by this job

Relocation assistance

Equity

Bonus

Benefits

Job summary

Inworld in Mountain View is seeking engineers to advance real-time, agentic AI systems at scale. You will own end-to-end deployment from research to production, optimizing latency and throughput on multi-GPU infrastructure.

Relocation assistance is offered; base salary ranges from $270,000 to $500,000 plus bonus, equity, and benefits; candidates with PhD or equivalent experience in CS/Physics/Math are welcome.

Qualifications

• PhD in CS, Physics, Math, or equivalent practical experience.
• Strong background in C++, CUDA, Rust, or optimized Python for high-performance computing.
• Experience with Kubernetes, Ray, multi-GPU/multi-node inference.
• Open-source contributions or public work in inference engines is a plus.
• Full-cycle ownership from research to production.

Responsibilities

• Own model from research to containerization and production.
• Optimize serving for low latency and high throughput.
• Collaborate on large-scale distributed systems and infrastructure.
• Contribute to open-source projects and publish technical write-ups.

Skills

Inference Optimization

Model Acceleration

High-Performance Systems

Distributed Systems & Scaling

Education

PhD in CS, Physics, Math, or equivalent practical experience

Tools

C++

CUDA

Rust

Python (optimized)

Job description

Inworld in Mountain View is seeking engineers to advance real-time, agentic AI systems at scale. You will own end-to-end deployment from research to production, optimizing latency and throughput on multi-GPU infrastructure.

Relocation assistance is offered; base salary ranges from $270,000 to $500,000 plus bonus, equity, and benefits; candidates with PhD or equivalent experience in CS/Physics/Math are welcome.