Senior AI Agent Platform Engineer

Sift Stack, Inc.; San Francisco (CA); Hybrid; USD 170,000 - 220,000; Full time

Benefits offered by this job

Equity

Relocation assistance

On-site offices

Job summary

Sift, the data infrastructure platform for hardware engineering teams, is seeking a product engineering leader to own a key customer-facing area of Sift Agents. You will talk to customers, decide what to build, and shepherd features from MVP to production, including dashboards, analysis scripts, and agent capabilities.

You will design and operate agentic systems over time-series data, build APIs, and scale Kubernetes-based workloads, ensuring reliability and observability across real-time

Qualifications

• 8+ years of professional software engineering experience.
• Ownership of a product area: talking to customers and shipping.
• Experience building APIs (REST, gRPC) and backend services in Go/Python/Rust.
• Working knowledge of distributed systems fundamentals.
• Curiosity about new AI products and willingness to try new agents and features.

Responsibilities

• Talk directly to customers to turn real review workflows into agent capabilities.
• Design, ship, and operate agentic systems for large-scale time-series data.
• Build tool interfaces, sandboxed execution, and memory management for agent code.
• Develop and maintain MCP server and APIs for agent capabilities.
• Create evaluation suites to measure quality, latency, cost, and failures.

Skills

8+ years software engineering

Product ownership

APIs (REST, gRPC)

Distributed systems

Curiosity about AI products

Tools

Go

Python

Rust

PostgreSQL

gRPC

Job description

Sift, the data infrastructure platform for hardware engineering teams, is seeking a product engineering leader to own a key customer-facing area of Sift Agents. You will talk to customers, decide what to build, and shepherd features from MVP to production, including dashboards, analysis scripts, and agent capabilities.

You will design and operate agentic systems over time-series data, build APIs, and scale Kubernetes-based workloads, ensuring reliability and observability across real-time