Baseten

Post-training applied researcher at Baseten building reward functions, training pipelines, and eval harnesses to fine-tune open-source LLMs for production use. Work directly with customers on domain-specific model training spanning healthcare, code generation, and agentic workflows.

Post-training research scientist at Baseten, an AI inference platform. Role spans pure research on model learning and alignment, plus applied work on training methodology and inference optimization for production systems serving companies like Cursor and Notion.

Software engineer at Baseten building internal AI agents and LLM-powered workflows to boost engineering productivity. Focus on evaluating, deploying, and customizing AI coding assistants and custom agents for the engineering org.

Forward Deployed Engineer at Baseten, an AI inference platform. You'll architect and deploy production AI applications for customers like Cursor and Notion, combining hands-on coding with customer-facing implementation and product work.

Software engineer at Baseten building training infrastructure for AI companies. Own features like multi-node training and serverless RL from conception to production, working across API, backend, and infrastructure layers.

Post-Training Research Engineer at Baseten building in-house tooling for custom model training. Focus on distributed GPU training, transformer parallelism, and performance optimization across the ML stack.

GPU Kernel Engineer at Baseten building high-performance CUDA kernels for ML inference optimization. Focus on matrix multiplications, attention mechanisms, and quantization for production AI systems.

Software engineer at Baseten building GPU networking and distributed inference infrastructure. Focus on RDMA integration, optimizing communication for multi-node LLM serving, and characterizing performance on cutting-edge hardware clusters.

Engineering Manager at Baseten leading a team focused on ML model inference and performance optimization. Responsibilities include managing engineers, optimizing LLM inference stacks, and driving production-scale ML deployment across frameworks like PyTorch, TensorRT, and CUDA.

Software engineer at Baseten optimizing ML model inference performance. Focus on quantization, speculative decoding, and LLM serving infrastructure using PyTorch, TensorRT, and CUDA.

Software engineer at Baseten building Model APIs infrastructure for LLM serving. Focus on distributed systems, GPU optimization, inference performance, and developer-facing API platforms.

Software engineer at Baseten building performance benchmarking and diagnostic tools for LLM inference infrastructure. Focus on GPU profiling, cluster validation, and automated performance testing across hardware stacks.

Software Engineer - Model Developer Ecosystem at Baseten, an AI inference platform. Build model library guides, evaluation frameworks, and developer education to help engineers select the right models for their use cases.

Product Manager at Baseten shaping the core developer experience for AI inference platform. Owns roadmap for APIs, SDKs, and UI workflows that enable teams to build and deploy AI applications.

Software Engineer on Baseten's Training Infrastructure team designing and architecting scalable ML training platforms. Focus on scheduling, storage, networking, and observability for distributed training workloads at scale.

Senior Enterprise Platform Engineer at Baseten building infrastructure for AI inference. Focus on multi-cloud capacity management, self-hosted clusters, enterprise security, and Kubernetes-based solutions for mission-critical AI workloads.

Software engineer at Baseten building core product infrastructure for ML model deployment. Work spans CLI tools, REST APIs, web applications, and Kubernetes infrastructure serving AI companies like Cursor and Notion.

Software engineer at Baseten building core platform capabilities for AI inference. Focus on API gateways, auth, quotas, metering, and multi-tenant isolation for production AI services.

Infrastructure Software Engineer at Baseten building ML inference platform components. Focus on Kubernetes deployments, resource management, and monitoring systems for production AI applications.

SRE at Baseten managing technical success for enterprise customers running ML inference workloads. Diagnose and resolve production issues across Kubernetes, networking, and model serving infrastructure.

Infrastructure Ops Engineer at Baseten managing GPU fleet operations and capacity fulfillment for AI inference. Coordinates hardware lifecycles, Kubernetes cluster maintenance, and customer capacity requests across global infrastructure.

Data Engineer at Baseten building internal data platforms and analytics infrastructure for an AI inference company. Design data models, pipelines, and metrics to support product, engineering, and business teams.

Solution Architect at Baseten, an AI inference platform. Partner with sales and customers on technical discovery, demos, and POC execution for ML model deployments. Scope solutions, run benchmarks, and guide customers through inference infrastructure tradeoffs.

Site Reliability Engineer at Baseten building scalable infrastructure for AI model inference and deployment. Focus on Kubernetes, CI/CD automation, multi-cloud capacity management, and operational excellence for mission-critical ML systems.