Senior Software Engineer, Voice AI – Data Infrastructure

This is a fully remote position, open to applicants in United States.

📋 Description

• Develop new product interfaces and workflows for jobs, customers, invoices, and scheduling utilizing React and React Native.

• Create AI chat interfaces capable of handling chat interactions, rendering tool results, providing streaming responses, facilitating human review, and incorporating feedback loops.

• Construct and manage production AI workflows, which include tool-using agents, retrieval-augmented generation (RAG)/search, classification/extraction, and human-in-the-loop processes.

• Contribute to the enhancement of WorkHero’s AI-driven business automation platform through new features and improvements.

• Take charge of real-time voice agents during live phone interactions, integrating telephony/WebRTC, facilitating streaming speech-to-text and text-to-speech, managing turn-taking, handling interruptions, and optimizing for latency.

• Enhance the reliability of the voice pipeline through strategies such as backpressure, failover, graceful degradation, and monitoring.

• Construct the call-data pipeline encompassing transcripts and events, including structured extraction and data warehousing.

• Create data models, analytics, and dashboards for conversation intelligence.

• Implement evaluations and monitoring for voice agents, focusing on quality, drift, cost, and latency.

• Scale cloud infrastructure utilizing infrastructure as code, queues, orchestration, and CI/CD methodologies.

• Analyze requirements and propose innovative solutions that leverage AI technologies.

• Produce clean, scalable code.

• Design, build, test, deploy, and manage the voice and data stack comprehensively.

• Optimize the performance, latency, and cost of real-time AI systems.

• Address critical system challenges and ensure ongoing reliability.

• Mentor colleagues and collaborate with product teams and subject matter experts.

• Grasp user needs and creatively tackle design challenges.

⛳️ Requirements

• Typically possess 5+ years of senior-level backend experience delivering production systems that the candidate has ownership of.

• Hands-on experience with real-time voice or streaming systems, including telephony (SIP/Twilio), WebRTC, streaming STT/TTS, LiveKit, or Pipecat, or similarly demanding real-time/streaming infrastructures.

• Fundamental knowledge in data engineering, encompassing event pipelines, data modeling, warehousing, and analytics on production data.

• Strong proficiency in a typed backend programming language; TypeScript is preferred, though comparable experience is welcome.

• Practical experience with features powered by large language models (LLMs), including usage, prompting, optimization, and AI architectures.

• Capability to work with infrastructure as code, including Terraform, cloud technologies, and CI/CD systems at scale.

• Ability to overlap at least 4 hours with the WorkHero team, preferably from 11am–3pm ET.

• Enthusiasm or willingness to utilize AI coding tools such as Claude Code and Cursor.

• Candidates from diverse backgrounds are encouraged to apply.

🏝️ Benefits

• Competitive salary and performance-based bonuses.

• Flexible working hours and remote work options.

• Opportunities for professional development and training.

• Comprehensive health benefits, including dental and vision.

• A supportive and inclusive company culture.