Senior IA Inference Engineer (AI)

Location: Paris, France; hybrid work setup with up to 2 remote days per week

Company

hirify.global develops cloud-native healthcare products for care teams and patients, using AI to improve access to and delivery of care.

What you will do

• Build shared self-hosted LLM serving foundations with MLOps engineers for open-weight models such as Gemma, Mistral, Llama, and Qwen.
• Define GPU capacity planning, deployment automation, model versioning, validation, promotion, and production model catalogs.
• Optimize vLLM, Triton Inference Server, and TensorRT-LLM for latency, throughput, batching, caching, quantization, parallelism, and cost per token across NVIDIA GPUs.
• Own production reliability through SLOs, load testing, safe rollouts, rollbacks, autoscaling, disaster recovery, on-call, and incident response.
• Build Datadog dashboards, alerting, and cost reporting for latency, GPU utilization, and inference spend.
• Work with Security and Privacy on network isolation, data residency, auditability, and the evolution toward Kubernetes-based orchestration.

Requirements

• 5+ years of software or computer engineering experience, including production experience with an LLM serving engine such as vLLM, SGLang, TensorRT-LLM, TGI, or Triton.
• Proficiency in Python and Terraform, with a strong understanding of transformer inference mechanics, including prefill, decode, KV cache, and batching.
• Experience running GPU workloads on Kubernetes or managed Ray/Anyscale platforms, designing reproducible benchmarks, and interpreting profiler output.
• Production reliability experience covering observability, incident response, and on-call responsibilities.
• Strong communication and collaboration skills, pragmatic build-versus-buy judgment, and comfort working in an evolving scope.
• Fluent English required.

Nice to have

• Experience with distributed serving frameworks, disaggregated prefill/decode, KV-cache-aware routing, Mixture-of-Experts, multimodal models, or LoRA adapters.
• GPU kernel or deep profiling experience with CUDA, Triton, or Nsight, or contributions to open-source inference projects.
• Experience in regulated environments and with GDPR, HDS, ISO 27001, or SOC 2.

Culture & Benefits

• Fully cloud-native technology platform supporting web and mobile products across countries and healthcare specialties.
• Free comprehensive health insurance for the employee and children, plus mental health and coaching services.
• 25 days of paid vacation and up to 14 RTT days.
• Work from abroad for up to 10 days per year through the flexibility days policy.
• Public transport reimbursement, lunch vouchers, work council subsidies, and employee value sharing through DoctoGrowth.
• Relocation support for international mobility and access to AI coding tools and dedicated training.

Hiring process

• 45-minute HR phone interview followed by a one-hour hiring manager interview.
• One-hour technical case study and a 90-minute behavioral interview.
• At least one reference check.