Senior Backend Engineer

People In AI; San Mateo (CA); Hybrid; USD 250,000 - 300,000; Full time

Job summary

People In AI in San Mateo is seeking a Senior Backend Engineer to build the infrastructure for an AI-native SaaS platform, with a focus on agent harnesses, orchestration, and production-grade systems.

You will own end-to-end development from prototype through deployment, working across data pipelines, geospatial and multimodal datasets, and collaborating with AI engineers to deliver reliable, scalable solutions for complex real-world problems.

Qualifications

• 5+ years of professional software engineering experience building complex applications or distributed systems.
• Strong Python engineering skills and production-quality software.
• Deep experience designing backend services, APIs, data models, and production systems.
• Experience building AI agent infrastructure, agent orchestration systems, LLM applications, or model-serving platforms.
• Reliability, state management, observability, latency, and failure handling in production systems.

Responsibilities

• Design and build production-grade backend services powering an AI-native SaaS platform.
• Build agent harnesses and execution infrastructure for sophisticated AI workflows.
• Develop systems for orchestrating multi-step agent interactions across models, tools, APIs, databases, and services.
• Design abstractions around tool calling, state management, retries, fallbacks, and failure recovery.
• Create agent runtimes supporting dynamic model-driven behavior and deterministic logic.
• Enhance infrastructure for evaluation, tracing, debugging, observability, and performance monitoring.
• Establish guardrails and execution patterns for reliable agentic workflows in production.
• Work on model routing, inference workflows, asynchronous execution, and long-running tasks.
• Collaborate with AI engineers to scale experimental capabilities into production systems.
• Build services supporting inference, optimization, and compute-heavy ML tasks.
• Design scalable data models for geospatial, regulatory, structured, unstructured, and multimodal data.
• Develop data ingestion/orchestration pipelines to serve agents and models.
• Develop reproducible deployment workflows and IaC practices.
• Own new technical capabilities end to end from prototype to production deployment.
• Help shape engineering patterns and architectural decisions as the platform scales.

Skills

Python

Backend engineering

Distributed systems

AI agent infrastructure

Reliability & observability

Education

Bachelor's degree in Computer Science or equivalent

Tools

APIs

Data pipelines

SQL/NoSQL

Job description

$250,000 - $300,000 Base + Equity

San Mateo - hybrid

An early-stage AI company building intelligent software for some of the most complex data, planning, and decision-making problems in the built environment.

The Company

We’re partnering with an early-stage AI company developing a production-grade AI platform designed to improve how complex development and planning decisions are made.

The team brings together engineers, AI researchers, scientists, and domain experts to tackle problems involving large-scale geospatial, regulatory, structured, unstructured, and multimodal datasets. At the heart of the product is an increasingly agentic platform: AI systems that need to reason across complex information, interact with tools and services, execute multi-step workflows, and reliably produce useful outcomes in real-world environments.

They are now looking for a Senior Backend Engineer to help build the infrastructure that makes those systems possible.

The Role

This is a broad, high-ownership engineering role sitting at the intersection of backend systems, AI agent infrastructure, data orchestration, and production ML.

A major part of your work will involve building the agent harnesses and runtime infrastructure surrounding AI models: the systems responsible for orchestrating agents, managing tool execution, coordinating multi-step workflows, maintaining state, handling failures, evaluating outputs, and connecting models to the data and services they need.

You’ll also build the backend services and data pipelines that underpin the wider platform, working with complex geospatial, regulatory, and multimodal datasets.

Rather than simply integrating an LLM API into an application, you’ll be helping answer the harder engineering questions around how agentic systems actually operate reliably in production.

You’ll own meaningful capabilities from initial prototype through architecture, implementation, deployment, observability, and iteration.

What You’ll Do

• Design and build production-grade backend services powering an AI-native SaaS platform.
• Build agent harnesses and execution infrastructure for sophisticated AI workflows.
• Develop systems for orchestrating multi-step agent interactions across models, tools, APIs, databases, and internal services.
• Design reliable abstractions around tool calling, structured outputs, state management, context management, retries, fallbacks, and failure recovery.
• Build agent runtimes capable of supporting both dynamic model-driven behaviour and deterministic application logic.
• Develop infrastructure for agent evaluation, tracing, debugging, observability, and performance monitoring.
• Create guardrails and execution patterns that make agentic workflows reliable enough for production use.
• Work on model routing, inference workflows, asynchronous execution, and long-running AI tasks.
• Partner closely with AI engineers to turn experimental agents and ML capabilities into scalable production systems.
• Build services supporting inference, optimization, machine learning models, and other computationally intensive capabilities.
• Design scalable data models and representations for complex geospatial, regulatory, structured, unstructured, and multimodal information.
• Build data ingestion and orchestration pipelines that give agents and models access to the right information at the right time.
• Develop reproducible deployment workflows and infrastructure-as-code practices.
• Own new technical capabilities end to end, from rapid prototype through hardened production deployment.
• Help establish engineering patterns and architectural decisions that will shape the platform as the company scales.

What You’ll Bring

• 5+ years of professional software engineering experience building complex applications or distributed systems.
• Strong Python engineering skills and experience writing maintainable, production-quality software.
• Deep experience designing backend services, APIs, data models, and production systems.
• Experience building AI agent infrastructure, agent orchestration systems, LLM applications, or model-serving platforms is highly valuable.
• A strong understanding of the engineering challenges surrounding production agentic systems: reliability, state, tool execution, observability, evaluation, latency, and failure handling.
• Experience building data orchestration workflows and working with large, messy, heterogeneous datasets.
• Comfort moving between application architecture, backend engineering, data infrastructure, and AI systems.
• Experience taking ambiguous technical problems from prototype to production.
• Strong systems thinking and an ability to determine when a problem should be solved through traditional software versus model-driven behaviour.
• The ability to collaborate closely with AI engineers, scientists, product managers, and domain specialists.
• A bachelor’s degree in Computer Science or equivalent practical experience.

Why Join?

This is an opportunity to work on the layer of AI engineering where some of the most interesting problems are emerging.

You won’t just be prompting models or building thin integrations around existing APIs. You’ll be developing the harnesses, runtime systems, backend services, and data infrastructure that allow AI agents to operate reliably against complex real-world problems.

You’ll have the opportunity to shape architectural decisions early, influence how agentic systems are designed and deployed, and own significant parts of the platform as it evolves from an early product into a scaled production system.

The role also offers unusual technical breadth. You could move from designing an agent execution abstraction, to debugging a multimodal data pipeline, to improving production inference infrastructure, to defining how a new AI capability should be deployed—all within the same environment.

For an engineer who enjoys building foundational systems, working close to applied AI, and taking genuine end-to-end ownership, this is a chance to have significant technical impact at an early stage.