Senior/Lead Machine Learning Engineer (AI)

TL;DR

Senior/Lead Machine Learning Engineer (AI): Developing and optimizing high-performance serving infrastructure for realtime multimodal models with an accent on inference acceleration and distributed systems. Focus on reducing latency, implementing advanced serving frameworks like vLLM, and scaling multi-GPU inference for thousands of concurrent queries.

Location: Must be based in Serbia. Future relocation to the US (San Francisco Bay Area) may be available with visa support.

Company

hirify.global is a product-oriented research lab developing best-in-class realtime multimodal models and a high-throughput orchestration platform.

What you will do

• Optimize inference using modern serving frameworks such as vLLM or TRT-LLM.
• Implement model acceleration via quantization, distillation, caching strategies, and speculative decoding.
• Build high-performance systems using C++, CUDA, Rust, or optimized Python.
• Scale distributed systems using Kubernetes and Ray for multi-GPU/multi-node inference.
• Own the full cycle of taking models from research, containerizing them, and ensuring reliable production serving.

Requirements

• Deep expertise in inference optimization and modern serving techniques.
• Proficiency in high-performance languages (C++, CUDA, Rust) or highly optimized Python.
• Experience with Kubernetes, Ray, and handling thousands of concurrent connections.
• Professional fluency in English (written and spoken) is required.
• Must be located in Serbia.

Nice to have

• PhD in CS, Physics, Math, or equivalent practical experience building backend/ML systems.
• Contributions to major open-source inference engines.
• Non-trivial systems programming projects or deep-dive technical write-ups.

Culture & Benefits

• Flat organizational structure with fast iterations and minimal process theater.
• Engineering culture that values impact and stability over purely theoretical optimizations.
• High ownership environment where performance, latency, and reliability are first-class features.
• Support for sharing work and making open-source contributions.
• Potential for future US visa and relocation support to the San Francisco Bay Area.