Voice AI Engineer for Real-Time Agentic Systems

Acto; United States; Remote; USD 140,000 - 210,000; Full time

Benefits offered by this job

Remote work option

Office access in Berlin

30 days vacation

Wellhub membership

Job summary

Acto is expanding its Agents team and seeks an experienced AI Engineer to build next-generation agentic AI systems powered by LLMs. You will work across chat, meeting preparation, recommendations, and voice, designing robust decision pipelines.

You will ship production-ready voice agents, integrate with APIs and data sources, and drive performance with experiments on latency, accuracy, and hallucinations. A startup mindset and collaboration with a small team are essential.

Qualifications

• Proven hands-on experience building voice agents in production.
• Strong experience with LLMs (e.g., OpenAI, Claude, Mistral).
• Familiarity with agentic frameworks (LangChain, LangGraph).
• Proficient in Python and modern ML tooling (Hugging Face, PyTorch, Ray).
• Experience with tool integration, APIs, memory/state management.
• Experience with simulation-based testing and evaluation of conversational and voice agents.

Responsibilities

• Design & Optimize Workflows: Design, implement, and optimize agentic workflows using LLMs across chat, meeting prep, and recommendations.
• Build Tool-Using Agents: Create agents that interact with external APIs, databases, and environments.
• Advance our Voice Agents: Push our voice-enabled agents forward, including pipeline design for real time conversation, transcription (ASR), speech synthesis (TTS), turn-taking, and dialogue management, with a focus on low latency and reliability.
• Integrate Memory & State: Implement retrieval, long-term memory, and state tracking into agent architectures.
• Deploy in Production: Collaborate with product teams to deploy agents in production and keep them healthy.
• Evaluate & Improve: Design and run experiments to evaluate agent performance, correctness, latency, and hallucination rates.
• Translate Product Needs: Turn high-level product requirements into scalable, testable agentic features.

Skills

Voice AI

LLM Expertise

Agentic Frameworks

Programming Proficiency

Tool Integration

Simulation-Based Testing

Startup Mindset

Tools

Python

Hugging Face

PyTorch

Ray

Job description

Acto is expanding its Agents team and seeks an experienced AI Engineer to build next-generation agentic AI systems powered by LLMs. You will work across chat, meeting preparation, recommendations, and voice, designing robust decision pipelines.

You will ship production-ready voice agents, integrate with APIs and data sources, and drive performance with experiments on latency, accuracy, and hallucinations. A startup mindset and collaboration with a small team are essential.