Databricks · 8 hours ago
Software Engineer - GenAI inference
San Francisco, CA
Full-time
Onsite
Mid Level
$142K/yr - $205K/yr
3+ years expDatabricks is the data and AI company that empowers organizations worldwide to unify and democratize data, analytics, and AI. As a software engineer for GenAI inference, you will design, develop, and optimize the inference engine to support the Foundation Model API, ensuring high performance and scalability for large language model serving systems.
AnalyticsArtificial Intelligence (AI)Data StorageInformation TechnologyMachine Learning
Responsibilities
Contribute to the design and implementation of the inference engine, and collaborate on model-serving stack optimized for large-scale LLMs inference
Collaborate with researchers to bring new model architectures or features (sparsity, activation compression, mixture-of-experts) into the engine
Optimize for latency, throughput, memory efficiency, and hardware utilization across GPUs, and accelerators
Build and maintain instrumentation, profiling, and tracing tooling to uncover bottlenecks and guide optimizations
Develop and enhance scalable routing, batching, scheduling, memory management, and dynamic loading mechanisms for inference workloads
Support reliability, reproducibility, and fault tolerance in the inference pipelines, including A/B launches, rollback, and model versioning
Integrate with federated, distributed inference infrastructure – orchestrate across nodes, balance load, handle communication overhead
Collaborate cross-functionally: with platform engineers, cloud infrastructure, and security/compliance teams
Document and share learnings, contributing to internal best practices and open-source efforts when possible
Qualification
Required
BS/MS/PhD in Computer Science, or a related field
Strong software engineering background (3+ years or equivalent) in performance-critical systems
Solid 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.)
Comfortable designing and operating distributed systems, 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 work closely with ML researchers, translate novel model ideas into production systems
Ownership mindset and eagerness to dive deep into complex system challenges
Preferred
Bonus: published research or open-source contributions in ML systems, inference optimization, or model serving
Benefits
Annual performance bonus
Equity
Company
Databricks
Databricks is a data and AI platform that unifies data engineering, analytics, and machine learning on a lakehouse architecture.
5001-10000 employees
H1B Sponsorship
Databricks has a track record of offering H1B sponsorships. Please note that this does not
guarantee sponsorship for this specific role. Below presents additional info for your
reference. (Data Powered by US Department of Labor)
Distribution of Different Job Fields Receiving Sponsorship
Represents job field similar to this job
Trends of Total Sponsorships
2025 (385)
2024 (319)
2023 (227)
2022 (222)
2021 (166)
2020 (64)
Funding
Current Stage
Late StageTotal Funding
$25.81BKey Investors
Counterpoint GlobalFranklin TempletonAndreessen Horowitz
2025-12-16Series Unknown· $4B
2025-09-08Series Unknown· $1B
2025-01-13Debt Financing· $5.25B
Leadership Team
Ali Ghodsi
CEO and Co-founder
David Conte
Chief Financial Officer
Recent News
Crunchbase News
2026-01-02
2025-12-29
globalventuring.com
2025-12-27
Company data provided by crunchbase