Software Engineer, Frontend (Agentic AI)

We Love AI Jobs; Northern (KY); Hybrid; USD 160,000 - 200,000; Full time

Job summary

Sift is seeking an experienced Frontend Engineer to craft the browser-based UI for Sift Agents, enabling real-time streaming responses and interactions with large telemetry datasets.

You will collaborate with product and backend teams to design, implement, and ship reliable agent interfaces and data visualizations, ensuring fast, smooth experiences across browsers.

Qualifications

• 3+ years of professional software engineering experience.
• Comfort building frontend surfaces for complex data-intensive apps.
• Strong ownership: talk to customers, ship features end-to-end.

Responsibilities

• Build frontend surfaces for Sift Agents, enabling streaming responses and long-running tasks.
• Render agent findings alongside telemetry while maintaining browser performance.
• Optimize UI with Web Workers, OPFS caching, and performance-focused patterns.

Skills

React

TypeScript

Web Workers

OPFS

WebGL

D3.js

WebAssembly

Tailwind

Next.js

Radix UI

Tailwind CSS

Tools

Next.js

Radix UI

Tailwind CSS

WebGL

D3.js

Job description

# Software Engineer, Frontend (Agentic AI)SiftMarina Del Rey, CA (Hybrid)Full-time$160,000 – $200,000 / yearUpload your resume once and Scout applies for youApply with ScoutShare this job:LinkedInXSave imageBuild the browser experience for Sift Agents, which help hardware engineers investigate anomalies and analyze telemetry. You’ll shape agent interactions and render their findings alongside large datasets, working with customers and backend engineers to deliver the product.* Permanent* Hybrid* 3+ years### Skills and expertiseReactTypeScriptWeb WorkersOPFSWebGLD3.jsWebAssemblyTailwind### Key responsibilities* Build Sift Agents frontend surfaces and interaction patterns for streaming responses, interruptions, and long-running tasks.* Render agent findings alongside large telemetry datasets while maintaining browser performance.* Improve browser performance and consistent agent interfaces using Web Workers, OPFS caching, and component-library patterns.## How this job comparesCompared with 1,047 open mid-level engineering jobs on October 10, 2026.Pay: This job pays $160K to $200K a year. The 452 open mid-level engineering jobs that publish US pay start at $138K on average, so this job starts about 16% higher.Similar open jobs: We Love AI Jobs lists 1,047 open mid-level engineering jobs at 274 companies.Remote work: This job is hybrid. 104 of the 1,047 mid-level engineering jobs (10%) are remote.AI in this role: High. AI is the core of the work: building, training or deploying AI systems. The frontend is dedicated to Sift Agents, with work centered on presenting agent responses, ongoing tasks, and findings to users. The role regularly turns AI agent behavior into dependable browser interactions.## Full descriptionAbout SiftSift is the data infrastructure platform for hardware engineering teams. We turn high-frequency telemetry into engineering insights for mission-critical machines: rockets, satellites, autonomous vehicles, energy systems, and defense platforms. Founded by former SpaceX engineers, we are building the review and analysis layer for the AI era of physical systems.About The Role:Hardware programs generate far more telemetry than any team can review by hand. Sift Agents is our answer: AI agents that work alongside hardware engineers, investigating anomalies, reviewing test and flight data, and answering in minutes questions that used to take a day of scripting.This role comes with real product ownership and autonomy. You will talk directly to customers to understand how they review their machines, decide what to build, and own it from first MVP through every iteration after it ships. The surface area is wide: one day you might be polishing the micro-interactions that make the chat experience feel great, the next you might be building a bespoke caching layer for the chat messages off the main JS thread. We’re heavy users of frontier agentic products ourselves and have strong opinions about what makes them great. Sift Agents is where we put those opinions to work.This is a product engineering role, not a research role. Most of the work is the hard part of making agents feel dependable in the browser: streaming interactions, long-running tasks, rendering agent output over large real-time datasets, and showing engineers exactly what an agent did and why.In This Role, You'll:• Talk directly to customers and partner with product to turn real review workflows into agent capabilities: generating dashboards, writing analysis scripts, and surfacing insights buried in their telemetry• Build the frontend surfaces where Sift Agents live, and make them feel great• Design the interaction patterns of agentic UX: streaming responses, long-running tasks, interruptions, and showing an agent’s work so engineers can trust it• Render an agent’s findings alongside the telemetry that backs them, and keep it fast even when the data is large• Push the browser to its limits when the data demands it: Web Workers, OPFS-backed caching, and stepping outside React when the framework becomes the bottleneck• Contribute to the component library to keep agentic UI patterns consistent across the product• Collaborate with backend and full stack engineers on the API design that powers agent sessionsThe Skillset You'll Bring:• 3+ years of professional software engineering experience• Get excited about owning a product area: talking to customers, deciding what to build, and shipping it• Have built complex, high-performance web applications with technologies like React, NextJS, TypeScript, or similar• Have an eye for detail: you notice the micro-interactions, latency, drops in FPS, and polish that separate good interfaces from exceptional ones• Are curious about new AI products: you try new agents, models, and features as they ship, and have opinions about what makes them goodIf this role excites you, apply even if you don’t check every box.Bonus Points:• Shipped products to users at scale: large data volumes, significant active user counts, or deep technical complexity• Shipped LLM-powered features• Built chat or agentic interfaces: streaming responses, tool-call rendering, long-running tasks• A strong understanding of web performance optimization and browser rendering• Worked with modern CSS (Tailwind) and component libraries (Radix UI) to build design systems• Used technical visualization tools (WebGL, D3.js, Apache ECharts), WebAssembly, and time-series data• Built tools for technical users (dashboards, data-editing environments)• A personal ecosystem of AI dev tooling: custom agents, skills, scripts, or workflows built to ship faster