Contribute to the design and implementation of the inference engine, and collaborate on model-serving stack optimized for large-scale LLMs inference
Collaborate with partners such as NVIDIA 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
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
Requirements
10+ years of engineering experience, with at least 5+ in infrastructure, platform, or backend systems roles.
Deep expertise in Kubernetes internals and operations , including networking, scheduling, scaling, and controller patterns.
Proven ability to design and build systems from scratch , making pragmatic tradeoffs along the way.
Strong proficiency in modern programming languages such as Python or Go. Experience building production-quality, reliable, and observable systems that are used across engineering organizations.
A growth-oriented mindset-driven to teach, learn, and improve systems as well as people.
Job Description:
DataRobot delivers AI that maximizes impact and minimizes business risk. Our platform and applications integrate into core business processes so teams can develop, deliver, and govern AI at scale. DataRobot empowers practitioners to deliver predictive and generative AI, and enables leaders to secure their AI assets. Organizations worldwide rely on DataRobot for AI that makes sense for their business - today and in the future.
As a Principal Software Engineer , you'll be responsible for technical leadership and vision. You'll lead by example-rolling up your sleeves as a technical contributor to solve complex problems, shaping architecture, and mentoring engineers to do their best work and advance their careers. You'll work across our control plane systems, influence cross-team roadmaps, and bring pragmatic engineering practices into how we build, test, and operate infrastructure software.
This is not a "stay in your swim lane" role. You'll question assumptions, challenge complexity, and help drive a high-performance culture. You'll be trusted to bring clarity where there's ambiguity, and momentum where there's inertia.
This role includes participation in an on-call rotation -we believe in shared ownership of our platform and aim to build systems that are resilient, observable, and require minimal intervention.
Datarobot · Boston, MA