Software Engineer, Full Stack (Agentic AI)

We Love AI Jobs; San Francisco (CA); Hybrid; USD 160,000 - 200,000; Full time

Job summary

Sift is hiring a Software Engineer, Full Stack to join the Agentic AI team in San Francisco, CA. The role blends frontend, API, and production-system work to build and operate Sift Agents—AI-powered tools that investigate anomalies and analyze telemetry.

You will own agent features, collaborate with customers, and ship MVPs through multiple iterations. We expect 3+ years of software engineering, experience with React and API services in Go, Python or Rust, and an interest in AI products and

Qualifications

• 3+ years of professional software engineering experience.
• Experience building frontend web apps with React, NextJS, or similar.
• Experience developing APIs or backend services with Go, Python, Rust, or similar.
• Interest in new AI products and agentic systems.

Responsibilities

• Turn customer telemetry review workflows into agent capabilities, such as dashboards and analysis scripts.
• Build and operate dependable agents, including tooling, sandboxed execution, context management, and guardrails.
• Develop APIs, frontend surfaces, evaluations, and production observability for agent workloads.
• Integrate frontier models and ensure scalable, reliable agent execution.

Skills

React

Go

Python

Rust

gRPC

Kubernetes

PostgreSQL

Tools

MCP

Job description

# Software Engineer, Full Stack (Agentic AI)SiftSan Francisco, CA (Hybrid)Full-time$160,000 – $200,000 / yearAI tools:MCPUpload your resume once and Scout applies for youApply with ScoutShare this job:LinkedInXSave imageBuild Sift Agents, a product that helps hardware engineers investigate anomalies and analyze telemetry using AI agents. You’ll work directly with customers and own agent features across the frontend, APIs, and production systems.* Permanent* Hybrid* 3+ years### Skills and expertiseReactGoPythonRustgRPCKubernetesPostgreSQLMCP### Key responsibilities* Turn customer telemetry review workflows into agent capabilities such as dashboards and analysis scripts.* Build and operate dependable agents, including tools, sandboxed execution, context management, and guardrails.* Develop APIs, frontend surfaces, evaluations, and production observability for agent workloads.## 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 role builds and operates Sift Agents, which use AI to investigate anomalies and answer questions about telemetry. It also involves integrating models and developing agent tools, evaluations, and guardrails.## Full descriptionAbout SiftSift is the data infrastructure platform for hardware engineering teams. Sift turns high-frequency telemetry into engineering insights for mission-critical systems. Teams use Sift to build and operate rockets, satellites, autonomous vehicles, energy systems, defense platforms, and more.Founded by former SpaceX engineers who built the tools behind Dragon and Starlink, Sift is building the data infrastructure to herald the AI era for physical systems.About the RoleHardware 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 frontend micro-interactions that make the chat experience feel great, the next you might be writing the Kubernetes scaling logic that orchestrates agent workloads. 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 dependable: tool design, context management, code execution environments, evaluation, and observability.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• Design, ship, and operate agentic systems that reason over large-scale time-series data and hardware domain context• Build everything around the model that makes agents dependable: tool interfaces, sandboxed execution for agent-generated code, context and memory management, custom compaction algorithms, opinionated skills, and guardrails• Develop and maintain Sift’s MCP server, the tool surface that lets both our agents and our customers’ AI tools query telemetry directly• Work across the whole stack• Build the frontend surfaces where Sift Agents live, and make them feel great• Design and implement the APIs that power our agentic capabilities• Run agents reliably at scale, both in the cloud and on-prem• Build evaluation suites that measure whether agents actually help engineers, and instrument quality, latency, cost, and failure modes in production• Integrate and assess frontier models across providersThe Skillset You'll Bring:• Have 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 frontend web applications with technologies like React, NextJS, or similar• Have built APIs (REST, gRPC, etc.) or backend services with technologies like Go, Python, Rust, or similar• 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 agentic systems: multi-step tool use, planning loops, context management, and evals• Designed tool ecosystems for agents, including MCPUpload your resume once and Scout applies for youApply with Scout