Job Description

Role Overview

We are seeking a high-caliber AI Research Engineer to bridge the gap between cutting-edge algorithmic research and high-performance system implementation. In this role, you will be the primary architect for optimizing the deployment of Large Language Models (LLMs), moving beyond treating GPUs as "black boxes" to treat them as resources to be saturated through meticulous kernel tuning and memory management.

You will focus on optimizing LLM deployment across diverse hardware profiles, from multi-GPU, multi-node high-performance server clusters to integrated GPU (iGPU) configurations in consumer-grade AI laptops. If you are a builder who thrives on squeezing every drop of performance out of silicon while maintaining model accuracy, you belong on our team.

Key Responsibilities

• Research & Model Development: Fine-tune pre-trained models using advanced techniques (LoRA, QLoRA, RLHF, full parameter tuning). Conduct experiments with emerging architectures like Mixture of Experts (MoE), sparse attention, and dynamic computation to enhance efficiency and safety.
• Architectural Optimization: Optimize inference engines for long-context windows, focusing on innovative KV cache management and compression. Profile and eliminate bottlenecks across the stack, specifically optimizing data transfer between NVMe storage, system memory, and GPUs.
• Hardware-Software Co-design: Implement advanced memory management strategies to push the boundaries of LLM serving on constrained hardware (iGPUs). Perform hardware-aware deployment to ensure maximum resource utilization.
• Software Design & System Integration: Develop and integrate scalable RESTful APIs (FastAPI) to support reliable application interactions. Build clean, maintainable full-stack components using JavaScript/TypeScript, Next.js, and React.
• Deployment & Containerization: Containerize complex AI workloads using Docker to ensure seamless consistency across development, testing, and production environments.
• Collaborative Engineering: Use Git-based workflows to collaborate with cross-functional teams, ensuring all software solutions align with established architectural, development, and testing standards.

Job Requirements

• Education: Bachelor’s degree in Computer Science, Data Science, Electrical Engineering, or a related technical field.
• AI & LLM Proficiency: Deep understanding of Machine Learning and Deep Learning. Hands-on experience with PyTorch, Hugging Face Transformers, and LLM API integration.
• Advanced AI Techniques: Proven experience or project work in Retrieval-Augmented Generation (RAG), Agent workflows, and multimodal Generative AI (text, voice, image).
• Backend & Systems Programming: Strong foundation in Python (FastAPI) and JavaScript/TypeScript. Experience with Linux (Ubuntu Server) and Nginx.
• DevOps Fundamentals: Proficiency in Docker for containerization and Git for version control.
• Startup Mindset: 0–2 years of experience (fresh graduates with strong project portfolios are encouraged); must have the ability to build the "first working iteration" in a fast-paced environment.

Nice-to-Haves

• Low-Level Tuning: Experience or knowledge in C++, Rust, or CUDA/Triton for kernel development and low-level performance tuning.
• Hardware Knowledge: Preliminary understanding of hardware architecture, specifically the interplay between SSDs, CPUs, and GPUs.
• Frontend Expertise: Experience building user-facing AI interfaces with React and Next.js.
• Testing & Tooling: Familiarity with Postman for API testing and VS Code for streamlined development.
  

Skills