Senior ML Engineer - Real-Time Inference at Scale

careers.bitkraft.vc - Jobboard; United Kingdom; On-site; GBP 140,000 - 200,000; Full time

Job summary

Inworld is seeking a Full-Time ML Engineer to develop cutting-edge multimodal models. This role requires strong technical expertise in high-performance systems and experience with distributed systems, Kubernetes, and C++.

The base salary ranges from £140,000 to £200,000, plus equity and benefits. Candidates must have the legal right to work in the UK, as visa sponsorship is not available now.

Qualifications

• Deep understanding of modern serving frameworks and techniques like vLLM or TRT-LLM.
• Hands-on experience with quantization, distillation, and caching strategies.
• Proficiency in C++, CUDA, Rust, or Python for performance optimization.
• Experience with Kubernetes, multi-GPU/multi-node inference.
• Non-trivial systems programming projects or open-source contributions.
• Ability to take a model from research to production.

Responsibilities

• Develop and optimize multimodal models for real-time applications.
• Design benchmarks and prototypes for unresolved problems.
• Ensure performance, reliability, and latency as product features.

Skills

Inference Optimization

Model Acceleration

High-Performance Systems

Distributed Systems & Scaling

Public work

Full-cycle ownership

Background in CS/Physics/Math

Education

PhD in Computer Science, Physics, Math, or equivalent

Tools

C++

CUDA

Rust

Python

Kubernetes

Ray

Job description

Inworld is seeking a Full-Time ML Engineer to develop cutting-edge multimodal models. This role requires strong technical expertise in high-performance systems and experience with distributed systems, Kubernetes, and C++.

The base salary ranges from £140,000 to £200,000, plus equity and benefits. Candidates must have the legal right to work in the UK, as visa sponsorship is not available now.