Backend AI Inference Engineer
2 hours ago
Winnipeg, Manitoba, Canada
Sarsfield Group
Full-time
Free with email or Google
Save this job and keep your search organized
Create a free account to save jobs, create alerts and return to this listing from your dashboard.
Free with email or Google
By continuing, you agree to our Terms & Privacy Policy.
Build AI inference systems with Python and PyTorch as a Backend Engineer, AI, powering production interactions through reliable, observable APIs.
You will own the inference and orchestration layer between models and users. The work covers production backend systems, AI-powered features, and service boundaries around models. You will optimize real-world performance while supporting mobile and desktop clients.
Key Responsibilities:
Build and operate backend systems serving AI features Design inference pipelines and orchestration layers Define service boundaries around models Monitor, log, alert, and respond to incidents Optimize latency and throughput across inference systems Requirements:
Experience running high-throughput, low-latency services Familiarity with LLMs, embeddings, and multimodal inference Experience with Python, NodeJs, and PyTorch Knowledge of SQL, noSQL, and Docker Bias toward shipping and learning from production behavior Apply backend engineering expertise across AI inference, orchestration, reliability, latency, and production API performance.
Build and operate backend systems serving AI features Design inference pipelines and orchestration layers Define service boundaries around models Monitor, log, alert, and respond to incidents Optimize latency and throughput across inference systems Requirements:
Experience running high-throughput, low-latency services Familiarity with LLMs, embeddings, and multimodal inference Experience with Python, NodeJs, and PyTorch Knowledge of SQL, noSQL, and Docker Bias toward shipping and learning from production behavior Apply backend engineering expertise across AI inference, orchestration, reliability, latency, and production API performance.