Senior / Staff Software Engineer, Agentic Platform

Location

San Francisco, CA

Work Arrangement: Hybrid
Position: Full-time
Company Stage: Series B
Experience: 4+ years of professional software engineering experience
Compensation: $220,000–$290,000 base salary + equity
Location Requirement: San Francisco, CA

Company Description

We are building an AI platform that helps large manufacturers improve product reliability and reduce the cost of poor quality.

The platform brings together fragmented operational data from across customer, service, field, telematics, warranty, and aftermarket systems to help engineering and manufacturing teams identify issues, understand root causes, and make better decisions.

A major part of the product is an advanced agentic platform that turns complex, unstructured real-world data into actionable insights. The systems being built are highly consequential: an agent's conclusions can influence decisions around product redesigns, quality investigations, and even recalls. Reliability, accuracy, and rigorous evaluation are therefore central to the engineering challenge.

The company is backed by significant venture funding and is working with major enterprise manufacturers. You'll join a growing engineering organization and help shape a new agentic engineering team, with the opportunity to influence the architecture and technical direction of a core product area.

What You Will Do

• Own agentic system architecture: Design and scale the core agentic systems, including orchestration, tool use, memory, retrieval, context engineering, evaluation, observability, and reliability guardrails.

• Build distributed systems: Architect and develop the infrastructure that takes complex customer data from ingestion through agent-driven reasoning to actionable root-cause insights.

• Solve complex data challenges: Build systems that transform fragmented, noisy, incomplete, and heterogeneous operational data into structured context that AI models can reliably reason over.

• Develop reliable reasoning infrastructure: Build and harden multi-step and multi-agent workflows, ensuring agents can reason effectively across large volumes of enterprise data.

• Establish evaluation frameworks: Develop rigorous testing and evaluation processes for non-deterministic systems, measuring agent accuracy against expert-validated ground truth.

• Measure real-world outcomes: Help evaluate system performance through meaningful customer outcomes, including detection rates, investigation speed, and warranty cost reduction.

• Shape the technical roadmap: Partner closely with Engineering and Product leadership to define the architecture, technical vision, and roadmap for the agentic platform.

• Improve engineering standards: Lead technical discussions, contribute to design documents, conduct code reviews, and establish best practices for building reliable agentic systems.

• Mentor other engineers: Provide technical guidance and mentorship to engineers, particularly around agentic architecture, distributed systems, and system design.

Ideal Candidate Background

Required Experience

• 4+ years of professional software engineering experience.

• Recent, hands-on experience building production agentic systems.

• Experience with LLM orchestration, tool/function calling, multi-step reasoning, and multi-agent systems.

• Understanding of retrieval, context engineering, memory, and MCP or comparable agent integration protocols.

• Experience designing, building, and owning complex distributed systems.

• Ideally, experience in data-intensive B2B SaaS environments.

• Strong understanding of the modern agentic technology stack and the infrastructure required to operate LLM-driven systems reliably.

• Experience building evaluation, testing, and observability frameworks for non-deterministic AI systems.

• Ability to work with messy, heterogeneous, and unstructured real-world data and make it usable for AI-driven reasoning.

• Strong system design and architectural decision-making skills.

• Experience providing technical mentorship and guidance to other engineers without requiring formal management authority.

• Ability to collaborate with Engineering and Product leadership to shape technical direction.

• Strong ownership mentality and ability to lead complex technical initiatives from design through production.

Technical Skills

Agentic Systems and LLM Engineering

• LLM orchestration.

• Tool and function calling.

• Multi-step reasoning.

• Multi-agent architectures.

• Agent memory and context management.

• Retrieval and context engineering.

• MCP or comparable protocols.

• Agent evaluation and testing frameworks.

• LLM observability and reliability guardrails.

Distributed Systems and Backend Engineering

• Distributed systems architecture.

• Data-intensive backend systems.

• Large-scale data ingestion and processing.

• System design and infrastructure ownership.

• Enterprise B2B SaaS platforms.

• Reliability, scalability, and fault tolerance.

Data and Evaluation

• Working with unstructured and heterogeneous data.

• Data normalization and contextualization.

• Building reliable data pipelines for AI systems.

• Expert-validated evaluation datasets.

• Measuring agent accuracy and performance.

• Evaluation against real-world customer outcomes.

Preferred Background

• Experience building production agentic platforms or AI-powered enterprise products.

• Experience with multi-agent orchestration and complex reasoning workflows.

• Experience building AI systems that operate on large, fragmented enterprise datasets.

• Background in data-intensive B2B SaaS.

• Experience working with manufacturing, industrial technology, automotive, or other complex enterprise environments.

• Experience building root-cause analysis, anomaly detection, or operational intelligence systems.

• Experience with LLM evaluation frameworks, observability tooling, and production monitoring.

• Experience designing systems where incorrect AI outputs can have significant operational or financial consequences.

• Experience leading architecture discussions and influencing engineering direction.

• Experience mentoring engineers and raising technical standards.

Working Style and Culture

• Strong technical ownership: Can independently own complex architecture and infrastructure decisions.

• Hands-on leadership: Remains deeply involved in implementation while guiding technical direction.

• Systems thinker: Understands how data ingestion, retrieval, reasoning, evaluation, and observability fit together.

• Quality-driven: Understands that reliability and correctness are essential when AI systems influence consequential decisions.

• Collaborative: Works effectively with Engineering and Product leadership.

• Mentor-minded: Helps other engineers improve through design reviews, code reviews, and technical guidance.

• Comfortable with ambiguity: Can help define architecture and best practices for a new and evolving engineering team.

Compensation and Benefits

• Base salary: $220,000–$290,000.

• Equity: Competitive equity package.

• Work arrangement: Hybrid.

• Location: San Francisco, CA.

• Openings: 3 full-time positions.

Why Join?

• Shape a new agentic platform: Help architect a core AI product area and influence its technical direction.

• Solve meaningful engineering challenges: Work with fragmented, complex enterprise data and build systems that turn it into actionable intelligence.

• Build consequential AI systems: Develop agentic workflows where accuracy and reliability directly influence important manufacturing and product-quality decisions.

• Own architecture at scale: Build distributed systems and reasoning infrastructure designed for enterprise-scale applications.

• Work with enterprise customers: Help solve real-world problems for large manufacturers.

• Influence engineering standards: Establish best practices for agentic systems, evaluation, observability, and reliability.

• Grow as a technical leader: Mentor engineers and partner with senior Engineering and Product leaders without moving away from hands-on technical work.