Machine Learning Engineer (AI)

TL;DR

Machine Learning Engineer (AI): Developing and optimizing high-performance model inference systems with an accent on latency, throughput, and cost efficiency. Focus on profiling GPU/CPU pipelines, implementing quantization techniques, and productionizing cutting-edge model architectures for real-world scale.

Location: Remote (World)

Company

hirify.global is a Series A startup focused on pushing the limits of model inference performance at scale.

What you will do

• Optimize inference latency, throughput, and cost for large-scale ML models in production.
• Profile and resolve bottlenecks in GPU/CPU inference pipelines, including memory, kernels, batching, and IO.
• Implement and tune advanced techniques such as quantization (fp16, bf16, int8, fp8), KV-cache optimization, and speculative decoding.
• Collaborate with research engineers to transition new model architectures into production-grade systems.
• Build and maintain inference-serving systems using Triton, custom runtimes, or bespoke stacks.
• Benchmark performance across diverse hardware (NVIDIA/AMD GPUs, CPUs) and cloud environments.

Requirements

• Strong experience in ML inference optimization or high-performance ML systems.
• Deep understanding of deep learning internals, including attention mechanisms, memory layout, and compute graphs.
• Hands-on proficiency with PyTorch and experience in model deployment.
• Familiarity with GPU performance tuning using CUDA, ROCm, Triton, or kernel-level optimizations.
• Proven experience scaling inference for real users beyond research benchmarks.
• Ability to work in a fast-moving startup environment with high ownership and ambiguity.

Nice to have

• Experience with LLM or long-context model inference.
• Knowledge of inference frameworks such as TensorRT, ONNX Runtime, vLLM, or Triton.
• Experience optimizing across different hardware vendors.
• Contributions to open-source ML systems or inference tooling.
• Background in distributed systems or low-latency services.

Culture & Benefits

• Real ownership over performance-critical systems with direct impact on unit economics.
• Competitive compensation package including meaningful equity at Series A.
• Close collaboration with research, infrastructure, and product teams.
• Engineering culture that prioritizes technical quality over hype.