Senior Software Engineer, Backend (Agentic AI)

Sift Stack, Inc.•Marina del Rey, CA

17h•$180,000 - $230,000•Hybrid

About The Position

Sift is a data infrastructure platform for hardware engineering teams, turning high-frequency telemetry into engineering insights for mission-critical machines. Sift Agents are AI agents that help hardware engineers investigate anomalies, review test and flight data, and answer questions about telemetry. This is a product engineering role focused on building dependable agentic systems, not a research role. The engineer will own a product area, work directly with customers to understand their workflows, decide what to build, and take features from MVP through ongoing iterations. The work spans agent tool interfaces, context management, code execution environments, evaluation and observability, as well as distributed systems and Kubernetes-based agent workload orchestration. The role also involves developing Sift’s MCP server and APIs, integrating frontier models, and ensuring agent performance and reliability in production. Sift’s headquarters is in Marina Del Rey, California, and the team collaborates in person on Mondays and Thursdays and meets for a full week every two months. Relocation to Los Angeles or work from the San Francisco office may be considered for the right candidate. U.S. person status is required for ITAR/EAR compliance.

Requirements

At least 8 years of professional software engineering experience.
Excitement about owning a product area, including talking to customers, deciding what to build, and shipping it.
Experience building APIs such as REST or gRPC and complex backend services with Go, Python, Rust, or similar technologies.
Working knowledge of distributed systems fundamentals.
Curiosity about new AI products, including trying new agents, models, and features and forming opinions about their quality.
Must be a U.S. citizen, lawful permanent resident, or protected individual such as an asylee or refugee, in compliance with ITAR/EAR regulations.

Nice To Haves

Experience shipping products to users at scale, involving large data volumes, significant active user counts, or deep technical complexity.
Experience shipping LLM-powered features.
Experience building agentic systems involving multi-step tool use, planning loops, context management, and evaluations.
Experience designing tool ecosystems for agents, including MCP.
Experience with sandboxed or isolated execution of generated code.
Experience operating production services, including Kubernetes, observability, and incident response.
Experience with streaming or time-series data systems such as Kafka, Flink, or TimescaleDB.
A personal ecosystem of AI development tooling, such as custom agents, skills, scripts, or workflows.
Background in time-series data, scientific computing, or hardware test and telemetry.
Experience building internal agentic tooling that accelerates an engineering organization.

Responsibilities

Work directly with customers and product partners to translate review workflows into agent capabilities, including generating dashboards, writing analysis scripts, and surfacing insights from telemetry.
Design, ship, and operate agentic systems that reason over large-scale time-series data and hardware-domain context.
Build systems that make agents dependable, including tool interfaces, sandboxed execution for agent-generated code, context and memory management, compaction algorithms, skills, and guardrails.
Build distributed systems that stream long-running agent work in real time, survive disconnects, and resume across restarts.
Design job-based execution systems that schedule, scale, and tear down agent workloads on Kubernetes in cloud and on-premises environments.
Develop and maintain Sift’s MCP server so agents and customers’ AI tools can query telemetry directly.
Design and implement APIs for agentic capabilities.
Build evaluation suites and instrument agent quality, latency, cost, and failure modes in production.
Integrate and assess frontier models across providers.