Software Engineer, Backend (Agentic AI)

Sift Stack, Inc.•Marina del Rey, CA

7h•$200,000 - $250,000•Hybrid

About The Position

Sift is seeking a Backend Software Engineer to join their Agentic AI team. This role focuses on building AI agents that assist hardware engineers by investigating anomalies, reviewing data, and answering questions quickly. The position offers significant product ownership and autonomy, involving direct customer interaction, product decision-making, and end-to-end ownership of features. Responsibilities span designing tool interfaces for agents, developing Kubernetes scaling logic, and making agents dependable through robust tool design, context management, code execution environments, evaluation, and observability. This is a product engineering role, not a research role, emphasizing the practical challenges of making AI agents reliable for hardware engineering workflows.

Requirements

3+ years of professional software engineering experience
Experience owning a product area: talking to customers, deciding what to build, and shipping it
Experience building APIs (REST, gRPC, etc.) and complex backend services with technologies like Go, Python, Rust, or similar
Working knowledge of distributed systems fundamentals
Curiosity about new AI products: trying new agents, models, and features as they ship, and having opinions about what makes them good

Nice To Haves

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 MCP
Worked with sandboxed or isolated execution of generated code
Operated services in production (Kubernetes, observability, incident response)
Worked with streaming or time-series data systems (Kafka, Flink, TimescaleDB)
A personal ecosystem of AI dev tooling: custom agents, skills, scripts, or workflows built to ship faster
A background in time-series data, scientific computing, or hardware test and telemetry
Built internal agentic tooling that accelerates an engineering org

Responsibilities

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
Build the distributed systems that let long-running agent work stream in real time, survive disconnects, and resume across restarts
Design job-based execution systems that schedule, scale, and tear down agent workloads on Kubernetes, both in the cloud and on-prem
Develop and maintain Sift’s MCP server, the tool surface that lets both our agents and our customers’ AI tools query telemetry directly
Design and implement the APIs that power our agentic capabilities
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 providers