Remote Senior Software Engineer - AI Voice & LLM

WW Talents; Madison (WI); Remote; USD 130,000 - 190,000; Full time

Job summary

Replicant is seeking a Senior Software Engineer with 5+ years of experience to join a small, high-impact team building AI-powered voice agents that handle millions of calls monthly for Fortune 500 companies. You will work across four product teams—three core and one forward-deployed—shipping full-stack features powering our LLM-based platform.

Responsibilities include building full-stack features, integrating speech recognition and TTS, and collaborating with product and ML teams in a

Qualifications

• 5+ years of experience as a software engineer, preferably in AI/ML or startup contexts.
• Proficiency in Python or TypeScript (one required).
• Experience shipping full-stack features at scale for millions of users.
• Hands-on experience with LLMs, multi-turn agents, or related tools.
• Ability to work across multiple product teams and ecosystems.

Responsibilities

• Build and ship full-stack product features that support and enhance Replicant's LLM-powered voice and chat products.
• Work across product teams to deliver capabilities that help win deals and scale the platform (including forward-deployed engineering work).
• Integrate speech recognition, text-to-speech, and conversational AI model improvements into production systems.
• Optimize and debug production systems balancing latency, cost, and user experience at enterprise scale.
• Collaborate closely with product and ML teams in a fast-moving startup environment where every engineer owns multiple initiatives.

Skills

Python

TypeScript

Full-stack engineering

LLM experience

Startup mindset

Tools

LangChain

Speech/Voice tech

Job description

Replicant is seeking a Senior Software Engineer with 5+ years of experience to join a small, high-impact team building AI-powered voice agents that handle millions of calls monthly for Fortune 500 companies. You will work across four product teams—three core and one forward-deployed—shipping full-stack features powering our LLM-based platform.

Responsibilities include building full-stack features, integrating speech recognition and TTS, and collaborating with product and ML teams in a