Sr. AI / Machine Learning Platform Engineer - Voice Agents

Responsibilities

• Primarily programming in Python. The company seeks language agnostic engineers who are able and interested to learn new technologies as needed.
• Time spent will be roughly 50% building a simulation and evaluation platform for AI agents, and 50% working on the framework used to build the AI agents.
• Designing, building, and enhancing a simulation and evaluation platform used to rigorously test, benchmark, and improve AI agents across a wide range of tasks and environments.
• Developing scalable evaluation frameworks, tooling, and methodologies to measure agent performance, reliability, decision quality, and failure modes.
• Build core frameworks, abstractions, and infrastructure used to develop, orchestrate, and deploy AI agents.
• Collaborating closely with other engineers to rapidly iterate on agent architectures, capabilities, and evaluation strategies.
• Creating systems that enable reproducible experiments, large-scale simulations, and data-driven optimization of agent behavior.
• Improving developer workflows, testing capabilities, and platform reliability to accelerate AI agent development and deployment.
• Analyzing evaluation results and agent behaviors to identify weaknesses, guide improvements, and drive overall system performance.
• Contributing to technical architecture and engineering best practices across both the agent framework and evaluation platform stack.

Qualifications

• 5-10 years of engineering experience in good organizations.
• Strong software engineering experience building complex backend systems, platforms, frameworks, or developer tooling.
• Experience designing or building evaluation, testing, simulation, benchmarking, or experimentation systems for AI/ML products or distributed systems.
• Strong programming skills in Python and/or other modern backend languages.
• Experience working with LLMs, AI agents, reinforcement learning systems, or other modern AI application architectures.
• Strong understanding of software architecture, scalability, reliability, and performance optimization.
• Experience building internal platforms, SDKs, APIs, orchestration systems, or infrastructure that enable rapid product development.
• Ability to analyze complex system behavior, debug issues, and improve reliability through data-driven approaches.
• Comfortable working in fast-moving, ambiguous environments with a high degree of ownership and autonomy.