Staff Software Engineer - GenAI inference
Leads architecture, development, and optimization of GenAI inference engine for high-throughput, low-latency LLM serving. Requires 6+ years in performance-critical systems, deep ML inference expertise, CUDA/GPU programming, and distributed systems.
About the job
About This Role
As a staff software engineer for GenAI inference, you will lead the architecture, development, and optimization of the inference engine that powers Databricks Foundation Model API. You’ll bridge research advances and production demands, ensuring high throughput, low latency, and robust scaling. Your work will encompass the full GenAI inference stack: kernels, runtimes, orchestration, memory, and integration with frameworks and orchestration systems.
What You Will Do
- Own and drive the architecture, design, and implementation of the inference engine, and collaborate on model-serving stack optimized for large-scale LLMs inference
- Partner closely with researchers to bring new model architectures or features (sparsity, activation compression, mixture-of-experts) into the engine
- Lead the end-to-end optimization for latency, throughput, memory efficiency, and hardware utilization across GPUs, and accelerators
- Define and guide standards to build and maintain instrumentation, profiling, and tracing tooling to uncover bottlenecks and guide optimizations
- Architect scalable routing, batching, scheduling, memory management, and dynamic loading mechanisms for inference workloads
- Ensure reliability, reproducibility, and fault tolerance in the inference pipelines, including A/B launches, rollback, and model versioning
- Collaborate cross-functionally on Integrating with federated, distributed inference infrastructure – orchestrate across nodes, balance load, handle communication overhead
- Drive cross-team collaboration: with platform engineers, cloud infrastructure, and security/compliance teams
- Represent the team externally through benchmarks, whitepapers, and open-source contributions
What We Look For
- BS/MS/PhD in Computer Science, or a related field
- Strong software engineering background (6+ years or equivalent) in performance-critical systems
- Proven track record of owning complex system components and driving architectural decisions end-to-end
- Deep understanding of ML inference internals: attention, MLPs, recurrent modules, quantization, sparse operations, etc.
- Hands-on experience with CUDA, GPU programming, and key libraries (cuBLAS, cuDNN, NCCL, etc.)
- Strong background in distributed systems design, including RPC frameworks, queuing, RPC batching, sharding, memory partitioning
- Demonstrated ability to uncover and solve performance bottlenecks across layers (kernel, memory, networking, scheduler)
- Experience building instrumentation, tracing, and profiling tools for ML models
- Ability to lead through influence - work closely with ML researchers, translate novel model ideas into production systems
- Excellent communication and leadership skills, with a proactive and ownership-driven mindset
Bonus: published research or open-source contributions in ML systems, inference optimization, or model serving
Skills
CUDA, Cublas, Cudnn, Nccl, Gpu Programming, Distributed Systems, Ml Inference, Quantization, Kubernetes, LLMs
Similar jobs
ML Engineering jobs
Talkiatry
United States
Staff-level engineer responsible for building AI agents and automation, evaluating developer AI tools, and driving adoption across the engineering organization. Requires 8+ years of software engineering experience plus production experience with LLMs, agentic systems, and applied machine learning.
Nuro
Mountain View, CA
Develop and productize online mapping models for autonomous navigation using real-world sensor data. The role requires deep ML expertise, robotics or computer vision experience, strong Python and deep learning framework skills, and a staff-level ability to deliver practical solutions.
Nuro
Mountain View, CA
Build and operate ML infrastructure for autonomy teams, including training and deployment pipelines, model observability, inference serving, and compiler platforms across hardware targets. Requires a degree, 3+ years of relevant experience, Python proficiency, and distributed-systems expertise.
Shield AI
San Diego, CA
Develop production C++ perception capabilities for autonomous systems, spanning algorithms, libraries, integration, validation, and release. The role requires deep expertise in at least one perception domain, strong systems debugging, and experience delivering maintainable software in complex robotics or real-time environments.
OnePay
United States
Design and productionize ML, deep learning, and LLM models for personalization, recommendations, and search systems. Requires 7+ years building production ML/AI with business impact and strong cross-functional collaboration skills.