AI Research Engineer (Kernel & Inference Optimization) 100% Remote WorldwideJoin Tether and Shape the Future of Digital FinanceAt Tether, we're not just building products, we're pioneering a integral financial revolution.
Our cutting-edge solutions empower businesses—from exchanges and wding assistants, LLM agents, automation, and AI‐assisted engineering workflows to prototype faster, solve problems, generate and validate code, improve testing, accelerate debugging, and increase overall engineering productivity.
This is not simply about using AI autocomplete.
We're looking for engineers who are comfortable incorporating tools such as Cursor, Claude Code, GitHub Copilot, coding agents, custom scripts, or AI‐assisted specifications into their day‐to‐day development process while maintaining strong engineering judgment and ownership.
You'll work closely with Product, CX stakeholders, designers, and backend engineers to turn operational requirements into reliable, intuitive, and scalable user experiences.
What You'll Be Doing
Design, develop, and maintain React / TypeScript features across CX domain modules, including operations tooling, agent presence, inbox workflows, queues, assignments, and internal applications.
Build and evolve reusable UI components, forms, tables, filters, dashboards, and complex operational workflows.
Work with technologies and patterns including Tailwind CSS, Tremor, Radix/shadcn, and Storybook.
Apply AI‐assisted and agentic software engineering practices to accelerate prototyping, implementation, testing, refactoring, documentation, and debugging.
Experiment with AI coding agents and automated workflows to improve engineering productivity and development quality.
Build data‐driven interfaces using TanStack Query, React Router, react-hook-form, and Zod.
Integrate frontend applications with BFF and backend APIs.
Work within a micro‐frontend architecture using Rspack and Module Federation, respecting domain boundaries and monorepo conventions.
Collaborate on API design and integration with FastAPI backend services, including OpenAPI contracts and BFF endpoints.
Ensure end‐to‐end correctness across workflows involving queues, agents, assignments, conversations, and operational metrics.
Contribute to authorization‐aware UX aligned with gateway permissions and domain‐level capability models.
Troubleshoot issues across the frontend BFF backend stack using both traditional debugging techniques and AI‐assisted workflows.
Ensure the reliability, accessibility, and performance of agent‐critical workflows running in production.
Participate in code reviews, architecture discussions,



technical decision‐making, and engineering best practices around type safety, linting, testing, and maintainability.
What You Bring
8+ years of software engineering experience, with a strong frontend‐oriented background.
Strong production experience with React and TypeScript.
Hands‐on experience actively using AI development tools and agentic workflows such as Cursor, Claude Code, GitHub Copilot, coding agents, AI‐assisted specifications, or similar tooling.
Ability to use AI as part of the engineering workflow while maintaining ownership over architecture, code quality, testing, and technical decisions.
Experience building complex product interfaces involving forms, tables, filters, dashboards, and multi‐step workflows.
Strong understanding of modern frontend development practices and component‐driven architectures.
Experience with modern bundlers such as Webpack, Rspack, or Vite.
Experience with Tailwind CSS or similar modern styling frameworks.
Experience consuming REST APIs and working with OpenAPI‐based services.
Ability to debug and troubleshoot issues across frontend and backend boundaries.
Experience with modern state management and server‐state patterns such as TanStack Query, React Context, and hooks.
Strong debugging, problem‐solving, and technical decision‐making skills.
Ability to collaborate effectively with Product, Engineering, and operational stakeholders.
Advanced English proficiency, both spoken and written.
Nice to Have
Experience designing or integrating AI‐agent workflows, AI‐powered interfaces, or automated support operations.
Experience with micro‐frontends or Module Federation.
Experience working with monorepos using pnpm, Turbo, Nmulation scenarios tailored to real‐world deployment challenges, specifically those encountered on low‐resource devices.
Set measurable criteria to ensure that these resources effectively evaluate model performance, latency, and memory utilization under various operational conditions.Analyze computational efficiency and diagnose bottlenecks in the serving pipeline by monitoring both processing and memory metrics.
Address issues such as suboptimal batch processing, network delays,



and high memory usage to optimize the serving infrastructure for scalability and reliability on resource‐constrained systems.Work closely with cross‐functional teams to integrate optimized serving and inference frameworks into production pipelines designed for edge and on‐device applications.
Define clear success metrics such as improved real‐world performance, low error rates, robust scalability, optimal memory usage and ensure continuous monitoring and iterative refinements for sustained improvements.A degree in Computer Science or related field.
Ideally PhD in NLP, Machine Learning, or a related field, complemented by a solid track record in AI R&D; (with good publications in A* conferences).
Must have knowledge of Metal Shading Language (MSL).
You should be comfortable writing custom compute shaders from scratch.Proven experience in low‐level kernel optimizations and inference optimization on mobile devices is essential.
Your contributions should have led to measurable improvements in inference latency, throughput, and memory footprint for domain‐specific applications, particularly on resource‐constrained devices and edge platforms.A deep understanding of modern model serving architectures and inference optimization techniques is required.
This includes state‐of‐the‐art methods for achieving low‐latency, high‐throughput performance, and efficient memory management in diverse, resource‐constrained deployment scenarios.Must have strong expertise in writing GPU kernels for mobile devices (i.e., smartphones) as well as a deep understanding of model serving frameworks and engines.
Practical experience in developing and deploying end‐to‐end inference pipelines, from optimizing models for efficient serving to integrating these solutions on resource‐constrained devices is required.Demonstrated ability to apply empirical research to overcome challenges in model serving, such as latency optimization, computational bottlenecks, and memory constraints.
You should be proficient in designing robust evaluation frameworks and iterating on optimization strategies to continuously push the boundaries of inference performance and system efficiency.Distributed Inference Systems: Designing and optimizing high‐performance inference engines using techniques like Tensor Parallelism, Pipeline Parallelism, and Expert Parallelism to handle massive models on GPU clusters.Deep understanding of the math and structure behind Diffusion Models and Vision TransformersUnderstanding of Pruning, Quantization, Flash attention, KV Cache, Speculative Decoding (Eagle) etc.
#J-*****-Ljbffr

📌 Gpu Kernel Engineer – Cuda, Triton & Accelerator Performance (Rosario)
🏢 Anyone AI
📍 Rosario