Opportunity at
DialpadSr. Software Engineer, AI / ML Inference Platform
Dialpad provides an AI-driven platform for customer experience, connecting human agents and AI capabilities to resolve customer issues in real time. The company is currently hiring…
Career Tools
About This Role
Dialpad provides an AI-driven platform for customer experience, connecting human agents and AI capabilities to resolve customer issues in real time. The company is currently hiring a Senior Software Engineer to join the AI / ML Inference Platform team. This position centers on developing the shared foundational architecture that supports model training, release workflows, and production inference systems. This is an implementation-focused role suited for an experienced engineer who wants…
Job Description
Dialpad provides an AI-driven platform for customer experience, connecting human agents and AI capabilities to resolve customer issues in real time. The company is currently hiring a Senior Software Engineer to join the AI / ML Inference Platform team. This position centers on developing the shared foundational architecture that supports model training, release workflows, and production inference systems.
This is an implementation-focused role suited for an experienced engineer who wants to build robust systems rather than provide operational support. The successful candidate will collaborate closely with natural language processing and automatic speech recognition scientists to translate research models into reliable enterprise services. Responsibilities span building GPU training infrastructure, optimizing serving runtimes for low latency and high throughput, and establishing automated release mechanisms.
The ideal candidate brings extensive background in backend engineering, cloud operations, and machine learning infrastructure. While direct participation in fundamental machine learning research is not expected, the person in this role must comprehend training workflows, model behavior, and evaluation metrics to effectively bridge the gap between science and production. Team members operate in an environment where artificial intelligence serves as a core driver for internal productivity and customer solutions.
Responsibilities
- Design and improve shared platform capabilities spanning training, evaluation, release processes, and production inference.
- Build and operate shared GPU training environments to support experimentation and workload scheduling.
- Develop production serving pathways focused on low latency, high throughput, and high availability.
- Partner with applied science teams to scale model capabilities into production designs.
- Establish automated release processes including shadow traffic, canary testing, and quick rollbacks.
- Construct evaluation and benchmarking infrastructure to track performance, resource utilization, and operational costs.
Requirements
- Seven or more years of professional software engineering experience with backend, infrastructure, distributed, or machine learning platforms.
- Background building or operating systems that support model training or model inference.
- Proficiency in Python, Go, or another backend-oriented language.
- Hands-on experience with Linux, containers, Kubernetes, cloud infrastructure, and deployment automation.
- Experience operating GPU workloads and managing hardware performance factors.
Qualifications
- Familiarity with ASR, speech processing, NLP, or large language models.
- Experience with GPU-based or distributed model training.
- Familiarity with model serving runtimes such as vLLM, Triton, or TGI.
- Knowledge of model development frameworks like PyTorch or JAX.
- Experience with GCP infrastructure, particularly GKE and related storage or networking services.
Core Skills
Benefits
- Competitive salary
- Comprehensive benefits package
- Opportunities for professional growth and training programs
- Access to AI tools to support daily work
- Inclusive office environment designed for collaboration
Frequently Asked Questions
Answers are based only on the employer’s listing; where it doesn’t say, neither do we.
What is the employment type for this position?
This is a full-time position.
What is the location or remote status for this job?
The source posting does not specify a location or remote status, though it mentions inclusive offices designed for collaboration.
What level of experience is required?
Candidates must have seven or more years of professional software engineering experience with backend, infrastructure, distributed systems, or machine learning platforms.
Is the salary stated in the posting?
No, the salary is not specified in the job posting.
Sample Interview Questions
AI-generated questions tailored to this specific role — a preview of the full practice set.