Latest AI JobsBrowse Jobs
Inworld AI logo

Senior / Lead Machine Learning Engineer, Serving - Serbia

Inworld AISerbiaML Engineering
Apply on company site
Salary
Not listed
Job type
Full-time
Posted
7 Apr 2026
Status
Open · checked 7d ago

About this role

Role Overview

Inworld AI is seeking a Senior / Lead Machine Learning Engineer to join the team in Serbia. This full-time position focuses on building high-performance serving infrastructure and real-time AI solutions for consumer-facing applications. The role suits adaptive engineers who thrive in ambiguous environments and want to optimize large-scale inference at massive volumes.

Key Responsibilities

Take machine learning models from the research team, containerize them, and optimize their serving for production environments.
Handle distributed systems, multi-GPU and multi-node inference, and custom load balancing to manage thousands of concurrent connections reliably.
Profile code and leverage hardware capabilities to extract maximum performance from NVIDIA GPUs.
Collaborate daily with United States-based leadership and engineering teams using professional English.

Requirements

Experience with inference optimization and modern serving frameworks such as vLLM or TRT-LLM.
Practical knowledge of model acceleration techniques including quantization, distillation, caching strategies, continuous batching, paged attention, and speculative decoding.
Proficiency in performance-driven programming languages and tools like C++, CUDA, Rust, or highly optimized Python.
Background with distributed systems and scaling tools such as Kubernetes and Ray.
Strong preference for candidates holding a PhD in Computer Science, Physics, Math, or equivalent practical experience building complex backend or machine learning systems.
Professional fluency in written and spoken English.

Skills and Tools

Python
Kubernetes
Rust
C++
CUDA
Ray
Large Language Models (LLMs)
vLLM and TRT-LLM serving frameworks

About the Company

Inworld AI operates as a research lab and inference provider specializing in real-time artificial intelligence for consumer applications. The organization builds first-party speech models, serves large language models, and powers modular APIs utilized by millions of users daily. Having raised over $125 million from prominent investors like Lightspeed Venture Partners, Microsoft's M12 venture fund, and Founders Fund, Inworld technology powers interactive experiences for industry leaders such as NVIDIA, Microsoft Xbox, and Niantic. The company has also been recognized globally by CB Insights and LinkedIn.

How to Apply

Interested candidates should visit the official Inworld AI careers page to submit their application.

Skills and tech stack

PythonKubernetesRustC++LLM

Questions candidates ask

Where is this job located?

This position is based in Serbia, with daily collaboration required alongside United States-based leadership and engineering teams.

What type of employment is this?

This is a full-time role within the Machine Learning Engineering department.

What technical skills are required?

Key technical competencies include Python, Kubernetes, Rust, C++, CUDA, Ray, and experience with modern serving frameworks like vLLM and TRT-LLM.

What kind of background is the company looking for?

Inworld AI looks for candidates with a PhD in Computer Science, Physics, Math, or equivalent practical experience building backend or machine learning systems.

How should I apply for this position?

You can apply directly through the official Inworld AI careers page.

Ready to apply?

The application is on the official Inworld AI careers page.

Apply on company site