Software Engineer (Agentic Systems)
About the role
As a core technical leader within our Agentic AI initiatives, you will shape the vision, architecture, and execution of Dialpad’s next-generation AI platform, moving the industry beyond passive copilots into autonomous workflow execution. Working closely with Product, Applied Research, Design, and executive leadership, you will build production-grade systems where AI agents reason, act, coordinate, and safely execute workflows. You will help pioneer an advanced multi-agent orchestration framework capable of real-time conversational reasoning and tool execution over massive enterprise datasets while fostering an AI-native engineering culture.
Responsibilities
- Drive Technical Strategy: Own the architectural roadmap and delivery of Dialpad’s Agentic infrastructure, core orchestration layers, memory architectures, and evaluation/observability systems.
- Build & Scale: Design and deploy scalable, multi-modal AI agents capable of autonomous support, real-time voice reasoning, and secure API tool execution across complex enterprise workflows.
- Mentor & Influence: Act as a technical anchor for the organization, raising the engineering bar, mentoring senior peers, and defining technical standards for an AI-native SDLC.
- Partner Cross-Functionally: Collaborate with leadership across Product, Engineering, and Applied Research to align technical execution with Dialpad’s long-term business strategy.
- Push the Frontier: Research and implement emerging agent frameworks, LLM inference optimization, advanced retrieval systems, and cutting-edge safety/policy guardrails to keep Dialpad at the absolute forefront of the "era of the agent."
Requirements
- Experience: 10+ years of relevant software engineering experience, with a proven track record of technical leadership (as a Staff, Senior Staff, or Principal Engineer) shipping complex, large-scale systems.
- Systems Background: Strong foundations in scaling distributed systems and production-grade infrastructure before evolving into applied AI, LLM platforms, and agentic architectures.
- Leadership: Ability to lead and grow a small group of engineers.
- LLM Platforms: Inference optimization and fine-tuning strategies.
- Data & Retrieval: Advanced retrieval systems and memory architectures.
- Agent Frameworks: Hands-on experience with frameworks like LangChain/LangGraph, CrewAI, or AWS/Google Agent ecosystems.
- AI Ops: Evaluation, observability, and safety frameworks for production AI systems.
- Real-Time Infrastructure: Streaming infrastructure and voice/conversational AI.
- Tool Integration: Tool use, API execution frameworks, and human-in-the-loop validation systems.
- Operational Excellence: Experience setting clear technical goals, identifying architectural risks, and systematically clearing tech-debt gaps.
- The 0→1 Archetype: Ability to thrive in ambiguity, build cutting-edge AI products from the ground up, and scale them into robust, self-sustaining enterprise systems.
Qualifications
- Experience leading and growing a small group of engineers.
- Hands-on experience with frameworks like LangChain/LangGraph, CrewAI, or AWS/Google Agent ecosystems.
- Experience with real-time infrastructure and voice/conversational AI.
- Experience with tool integration and human-in-the-loop validation systems.
- Experience with advanced retrieval systems and memory architectures.
- Experience with AI Ops, including evaluation, observability, and safety frameworks for production AI systems.
- Experience with inference optimization and fine-tuning strategies.
- Experience with emerging agent frameworks, LLM inference optimization, and advanced retrieval systems.
- Experience with cutting-edge safety/policy guardrails.
Skills
- Experience in scaling distributed systems and production-grade infrastructure.
- Strong foundations in applied AI, LLM platforms, and agentic architectures.
- Ability to lead and grow a small group of engineers.
- Hands-on experience with frameworks like LangChain/LangGraph, CrewAI, or AWS/Google Agent ecosystems.
- Experience with real-time infrastructure and voice/conversational AI.
- Experience with tool integration and human-in-the-loop validation systems.
- Experience with advanced retrieval systems and memory architectures.
- Experience with AI Ops, including evaluation, observability, and safety frameworks for production AI systems.
- Experience with inference optimization and fine-tuning strategies.
- Experience with emerging agent frameworks, LLM inference optimization, and advanced retrieval systems.
- Experience with cutting-edge safety/policy guardrails.
Benefits
Work at the center of the AI transformation in business communications
Build and ship agentic AI products that are redefining how companies operate
Join a team where AI amplifies every employee’s impact
Competitive salary, comprehensive benefits, and real opportunities for growth
Pay
For exceptional talent based in California, the target base salary range for this position is posted below. Our salary ranges are determined by role, level, and location. The range displayed on each job posting reflects the target range for new hire salaries for the position. Within the range, individual pay is determined by work location and additional factors, including job-related skills, experience, and relevant education or training.
Schedule
This position reports directly to our Senior Director of Engineering and has the opportunity to be based in our San Francisco office.