AI Infrastructure & Experience Engineer

FocusKPI is seeking an AI Infrastructure & Experience Engineer to join one of our clients, a high-tech SaaS company.

Work Location: Mountain View, CA (Onsite role, 5 days/week onsite)
Duration: 4-month contract
Pay Range: $70 - 79/hr

**No C2C resumes are considered**

Position Responsibilities:

• Inference Optimization: Deploy and tune multiple LLMs and generative multimodal models on local inference hardware. Optimize performance metrics (TTFT, tokens/sec) via model quantization, caching strategies, and architecture-specific adjustments.
• Systems Engineering & CUDA: Leverage deep knowledge of the CUDA environment to build custom kernels, ensuring maximum utilization of the low-cost GPU compute.
• Orchestration & Integration: Seamlessly bridge inference backends with orchestration layers (LiteLLM, Ollama, etc.) and frontends like OpenWebUI.
• Rapid Prototyping: Build functional, high-fidelity demos showcasing model memory capabilities, agentic workflows, and context-aware web search.
• Peripheral Connectivity: Implement communication protocols to bridge local AI compute with peripheral devices, including smart TVs, household appliances, and XR hardware.

Requirements/Technical qualifications:

• Recent experience in model optimization is required
• Hardware & Compute: Proven experience with NVIDIA ecosystems and ARM64 architecture.
• Systems Programming: Advanced proficiency in C++, Python, and Rust. Deep familiarity with CUDA and the ability to author/debug custom CUDA kernels for compute-intensive tasks.
• AI/ML Frameworks: Extensive experience with modern inference engines (llama.cpp, TensorRT-LLM, Ollama) and orchestration frameworks (LiteLLM).
• Software Engineering: Robust understanding of asynchronous programming (FastAPI), containerization (Docker/Kubernetes), sandbox environments, and API design for low-latency communication.
• Full-Stack Prototyping: Ability to quickly spin up modern frontend UIs (React, Next.js, or similar) to present AI-driven intelligence to end users.
• Communication Protocols: Familiarity with WebSockets, gRPC, and REST for device-to-device communication in a local network environment.
• Overall Mandatory skills required: Model optimization recent experience, Interference Optimization, NVIDIA ecosystems, Custom CUDA Kernel Development, ARM64 architecture, Python

Ideal Candidate Profile:

• A minimum of 3 years of relevant industry experience is required
• The "Builder" Mindset: You are energized by the prospect of building proofs-of-concept in days rather than months. You thrive in environments where speed and creativity are paramount.
• Problem Solver: You approach unsolved, messy engineering challenges with enthusiasm rather than trepidation.
• Architectural Vision: You see the "big picture" of how AI becomes part of consumers' daily lives, not just how the model generates text.
• Agile & Adaptable: You are comfortable working in a fast-paced environment where priorities shift based on the results of rapid experimentation.
• Degree in Computer Science, Machine Learning, or Artificial Intelligence Specialization preferred, but not required

**No C2C resumes are considered**

Thank you!

FocusKPI Hiring Team

Founded in 2010, FocusKPI, Inc. (FocusKPI) is a data science and technology firm specializing in predictive analytics practice and methodologies. FocusKPI is a US company headquartered in Silicon Valley, California, with an East Coast office in Boston, Massachusetts.