AI/ML Infra / Systems Engineer (Inference)

7 hours, 25 minutes ago
Full-time
Senior
Software Development
Sapience AI

Sapience AI

Sapience AI is a small, privately held company focused on providing Institutional Knowledge Infrastructure for professional associations and membership organizations. The company emphasizes the integration of domain-specific AI systems with human expertise to enhance collaborative general intelligence. Its offerings include software applications, APIs, data analytics tools, and a secure platform designed to help organizations improve productivity and decision-making. In addition to its knowledge infrastructure, Sapience AI is developing a next-generation GPU cloud service, utilizing high-performance European data centers and NVIDIA hardware. This GPU-as-a-Service solution targets enterprises that require secure AI infrastructure and strict data residency controls. The company aims to support a variety of users, including professional organizations, academic institutions, and research organizations, by delivering innovative tools and insights tailored to their specific needs.

information technology & services
11-50
Founded 2024
$9M raised

Description

  • Build and operate end-to-end inference systems for MINERVA and COGENT.
  • Optimize model execution, batching, caching, retrieval, latency, and throughput.
  • Scale inference through autoscaling, load management, and graceful degradation.
  • Own GPU efficiency, inference economics, utilization, and capacity planning.
  • Create safe model deployment, versioning, rollout, and rollback processes.
  • Develop observability, dashboards, alerts, and operational tooling for serving systems.
  • Evaluate accelerators, runtimes, and serving frameworks for performance, cost, and maintainability.
  • Collaborate with Applied AI, Neuro-Symbolic AI, Platform Engineering, and Research teams.

Requirements

  • 5+ years of infrastructure, systems, or ML infrastructure engineering experience.
  • Hands-on experience serving ML or LLM models in production at scale.
  • Strong knowledge of latency, throughput, performance optimization, and distributed systems.
  • Experience with GPUs or accelerators and their efficient use.
  • Strong systems programming fundamentals and experience with Python plus Go, Rust, or C++.
  • Experience building reliable, cost-aware production systems with observability and operational excellence.
  • Experience with inference frameworks or runtimes such as vLLM, TensorRT, or Triton (preferred).
  • Experience optimizing LLM inference through batching, quantization, and caching (preferred).
  • Experience with Kubernetes, containers, cloud platforms, caching, queuing, and load-management systems (preferred).
  • Familiarity with retrieval systems, AI workload cost ownership, or neuro-symbolic and agentic systems (preferred).

Benefits

  • Base salary of $204,000–$216,000.
  • Early-stage equity.
  • Generous health and wellness benefits.
  • Equal opportunity workplace with application accommodations available.

Interested in this position?

Apply directly on the company website

Apply Now

Similar Roles

Freelance Translator Side Job - English & Chinese Voice Recordings - AI trainer

Toloka 251-1K Internet Software & Services

Record natural 1–2 minute English-Chinese bilingual voice clips for an AI training platform, sharing everyday thoughts and reactions in your usual conversational style.

7 hours, 25 minutes ago

Native Chinese Speaker Jobs - Voice Recordings, English & Chinese - AI trainer

Toloka 251-1K Internet Software & Services

A project-based AI training platform is seeking bilingual English-Chinese speakers to record natural, casual voice clips for language data development on a flexible, paid-per-recording basis.

7 hours, 25 minutes ago

Part-time Student Job - Paid Voice Recordings, English & Chinese - AI trainer

Toloka 251-1K Internet Software & Services

A bilingual freelance voice contributor records short, natural English-Chinese conversations for an AI training platform, completing approved clips on a flexible schedule.

7 hours, 25 minutes ago

GenAI Senior Integrated Designer

Brandtech+ 501-1000 Marketing services

Brandtech+ is seeking a remote GenAI Senior Integrated Designer to create and deliver digital, social, e-commerce, motion, and brand campaign assets using traditional design and GenAI workflows.

Digital Marketing Figma Generative AI Instagram API TikTok
1 day, 6 hours ago

You're on a roll! Sign up now to keep applying.

Sign Up

Already have an account? Log in

Used by 14,729+ remote workers