Latest AI JobsBrowse Jobs
B

Software Engineer - Voice AI (Inference Runtime)

BasetenSan FranciscoEPD
Apply on company site
Salary
$165K - $330K USD
Job type
Full-time
Work mode
Remote
Posted
23 Apr 2026
Status
Open · checked 7d ago

About this role

Role Overview

Baseten is hiring a Software Engineer for Voice AI focused on the inference runtime, operating out of San Francisco with remote flexibility available. This high-impact position suits an experienced systems builder ready to lead the end-to-end development of in-house voice AI infrastructure.

Key Responsibilities

Own and direct Voice AI product areas completely, handling everything from architectural design to rollout and production maintenance.
Build and operate real-time, large-scale, high-performance model serving platforms for text-to-speech, speech-to-text, and voice agent workloads.
Partner collaboratively across engineering groups to resolve full-stack technical hurdles and ensure synchronized product delivery.
Provide guidance to colleagues through technical leadership, detailed design documents, and thorough code reviews.

Requirements

Hold a Bachelor degree or higher in Computer Science or an equivalent technical discipline.
Demonstrate a solid history of managing production-level, real-time, large-scale systems where minimizing tail latency is critical.
Exhibit strong coding competence in at least one popular programming or scripting language, with Python expertise considered an asset.
Possess a strong product sense, specifically regarding developer-focused tooling.
Maintain an active interest in machine learning infrastructure paired with a readiness to learn.
Display excellent communication skills and effective teamwork abilities.
Utilize AI coding assistants like Cursor, Claude Code, or Codex daily to boost engineering output.

Nice to Have

Background in executing pipeline-level runtime improvements like dynamic batching, asynchronous scheduling, or decode-side throughput enhancements.
History of designing developer platforms including APIs, SDKs, CLIs, and self-serve workflows for infrastructure or machine learning solutions.
Familiarity with containerization tools and orchestration platforms such as Kubernetes, Docker, distributed scheduling, or service meshes.
Knowledge of audio and speech machine learning models like text-to-speech, speech-to-text, or speech-to-speech systems.
Experience working with model serving runtimes including vLLM, TensorRT, or ONNX.
Understanding of systems-level performance profiling across host and device boundaries using tools like PyTorch Profiler and diagnosing GPU efficiency bottlenecks.
Exposure to customer-facing engineering tasks such as technical discovery, pre-sales prototyping, or partnering directly with clients.

Skills and Tools

Python
PyTorch
Kubernetes
Docker
Spark

Salary and Benefits

Competitive salary ranging from $165,000 to $330,000 USD per year along with meaningful equity.
Full 100 percent health, dental, and vision insurance coverage for employees and their dependents within the United States.
Flexible paid time off alongside a company-wide winter break closing offices from Christmas Eve through New Year's Day.
Paid parental leave programs.
Access to a fertility and family-building stipend facilitated through Carrot.
U.S. company-facilitated 401(k) retirement plan.
Direct exposure to numerous machine learning startups providing unique networking and learning growth.

About the Company

Baseten supports mission-critical inference systems for prominent artificial intelligence enterprises. By combining applied research, adaptable infrastructure, and developer tools, the organization empowers frontier companies to launch advanced models into production environments. Backed by major investors following a Series F funding round, the team is expanding quickly to build the platform relied upon by engineers everywhere.

How to Apply

Interested candidates should visit the official Baseten careers page to submit an application and learn more about open opportunities.

Skills and tech stack

PythonPyTorchKubernetesDockerSpark

Questions candidates ask

Where is this job located?

The role is based in San Francisco with remote work options available.

What is the compensation range for this position?

The annual salary ranges from $165,000 to $330,000 USD, supplemented by meaningful equity.

What qualifications are required for applicants?

Candidates need a Bachelor's degree or higher in Computer Science or a related field, a background in managing real-time systems where tail latency matters, programming proficiency with Python as a plus, developer tool intuition, enthusiasm for machine learning infrastructure, strong communication skills, and fluency with AI coding assistants.

What benefits are provided to U.S.-based employees?

U.S. employees receive 100% medical, dental, and vision coverage for themselves and dependents, a company-facilitated 401(k), flexible PTO with a winter break, paid parental leave, and a fertility and family-building stipend through Carrot.

How should I submit my application?

You can apply directly through the official Baseten careers website.

Ready to apply?

The application is on the official Baseten careers page.

Apply on company site