Baseten

Baseten is seeking a Post-Training Research Engineer to build in-house tooling for post-training AI models at scale. This role involves deep technical dives into ML techniques, distributed computing, and systems-level concepts to support customer custom models, which are critical for Baseten's inference platform.

Post-training researcher focused on fine-tuning open-source LLMs for specific customer tasks using RL and reward engineering. Involves building training pipelines, environments, and evals, and working with customer data to improve models that reach millions of users.

Research Scientist focused on post-training methodology and performant inference, with a significant portion dedicated to pure research and the remainder to applied research informing the company's platform and customer needs. The role involves designing and executing experiments, publishing at top venues, and collaborating with engineering teams to translate research into production systems.

Software Engineer focused on optimizing GPU kernels for ML inference, including matrix multiplications, attention mechanisms, and quantization, using CUDA and PTX assembly.

Engineering Manager for Forward Deployed Engineering team focused on building, scaling, and optimizing LLM inference workloads for Baseten customers. This role involves hands-on technical ownership, team leadership, and collaboration with product and infrastructure teams to ensure best-in-class performance, reliability, and cost efficiency of AI applications on Baseten's platform. The role contributes to the core codebase and drives feature roadmap, acting as a player-coach.

Manager for a Solutions Architect team focused on enabling customers to deploy and optimize AI/ML models, particularly LLMs, on Baseten's inference platform. The role involves leadership, technical guidance, customer discovery, and ensuring high performance, reliability, and cost efficiency of AI applications in production.

Software Engineer focused on building and optimizing the inference runtime for Voice AI models, including state-of-the-art open-source models. The role involves developing large-scale, real-time infrastructure for multi-model voice agents, reducing latency, increasing throughput, and improving GPU efficiency. It also includes designing iteration loops for voice model customization and customization.

Software Engineer role focused on optimizing and operating Model APIs for AI inference, involving distributed systems, model serving, and developer experience. The role emphasizes performance improvements, structured outputs, tool/function calling, and multi-modal serving.

Engineering Manager for Model Performance at Baseten, a company providing inference infrastructure for AI companies. The role involves leading a team of engineers to optimize ML model inference and performance, focusing on production-level AI/ML solutions and scaling large models. Requires a strong engineering background, leadership experience, and expertise in ML performance optimization, with hands-on work in areas like TensorRT, PyTorch, and CUDA.

Software Engineer focused on ML performance for LLM inference, optimizing techniques like quantization and speculative decoding, and debugging ML performance issues in libraries like TensorRT and PyTorch.

Solution Architect role focused on AI/LLM inference, partnering with Sales and customers to design and deploy technical solutions. Responsibilities include customer discovery, technical scoping, leading demos, managing deployments, and driving POC execution. Requires an AI/ML background and customer-facing communication skills, with the ability to script and prototype.

This role focuses on partnering with customers to architect, build, and deploy high-scale production AI applications on Baseten's platform. It involves owning the customer journey from exploration to deployment, translating business goals into reliable, observable services with clear quality, latency, and cost outcomes. The role blends engineering, product management, technical customer success, and pre-sales solution engineering.

AI Solutions Engineer role focused on partnering with customers to architect, build, and deploy high-scale production AI applications on Baseten's platform. This involves owning the customer journey from exploration to production, translating business goals into reliable, observable services with clear quality, latency, and cost outcomes. The role blends engineering, product management, technical customer success, and pre-sales solution engineering.

Solution Architect role at Baseten, a company providing AI inference infrastructure. The role involves partnering with Sales and customers to understand business needs, design technical solutions, run technical discovery, and guide deployments and proofs of value. Responsibilities include customer discovery calls, technical scoping, leading demos, owning benchmarking and repeatable deployments across various AI modalities, advising on infrastructure tradeoffs, and driving POC execution. Requires an AI/ML background, strong customer-facing communication, and technical depth to scope solutions.

Baseten is seeking an AI Enablement Engineer to own and develop AI-powered tooling and agent infrastructure for internal productivity. This role involves evaluating, customizing, and deploying AI coding agents and building custom internal agents for tasks like incident triage and codebase Q&A. The engineer will also track usage, measure impact, and stay updated on AI tooling advancements to enhance the engineering organization's effectiveness across the SDLC.

Software Engineer focused on GPU Networking and Distributed Systems to optimize AI inference infrastructure, specifically for LLMs and multi-modal models. The role involves integrating RDMA, optimizing networking layers for disaggregated KV cache and WideEP, enabling fast startup speeds, and building observability tools for bleeding-edge hardware.

Software Engineer focused on building and shipping training products for AI companies, working across the full stack from API to infrastructure, including fine-tuning models and partnering with research engineers. The role involves developing features like multi-node training and serverless RL, with a focus on developer experience and reliability.

Software Engineer role focused on building and optimizing the performance of AI inference infrastructure, including benchmarking, hardware profiling, and developing automated testing and monitoring tools for LLMs.

Software Engineer on the Training Infrastructure team responsible for architecting and leading development of the ML training platform, focusing on scheduling, storage, networking, reliability, and observability for research engineers and model developers.

Software Engineer focused on building and maintaining the ML inference platform, enabling high-performance deployment, scaling, and monitoring of AI models for production applications.

Software Engineer on the Core Product team at Baseten, building and maintaining the core Baseten product that enables users to deploy and get value from ML models. The role involves working across the stack, including CLI tools, REST APIs, and the web application, with a focus on new feature development, API design, and bug fixing. Example initiatives include chains for multi-component workflows, asynchronous inference, model APIs, and model training for production inference.

The Forward Deployed Engineer partners with customers to architect, build, and deploy high-scale production AI applications on Baseten's platform. This role involves owning the customer journey from exploration to production, translating business goals into reliable services with clear quality, latency, and cost outcomes. It blends engineering, product management, technical customer success, and pre-sales solution engineering.