Software Engineer, Backend

About the role

Sift constructs data infrastructure for hardware engineering teams working on satellites, rockets, and autonomous systems. You will join our team to develop Sift Agents, an AI-driven layer that automates the analysis of complex telemetry data. This position focuses on product engineering, where you will own features from initial concept through production deployment. You will partner closely with domain experts to ensure that the data infrastructure meets the rigorous demands of aerospace and defense. The role requires a balance of deep technical execution and strategic thinking to solve ambiguous problems. You will be responsible for the reliability and performance of systems that handle critical telemetry streams. Your work will directly influence how engineering teams make decisions about complex hardware systems.

Key facts

What you'll do

• Collaborate with customers to translate manual data review workflows into automated agent capabilities.
• Architect and maintain systems that allow AI agents to reason over massive time-series datasets.
• Develop the infrastructure for agent reliability, including sandboxed code execution, memory management, and tool interfaces.
• Manage distributed job execution on Kubernetes to handle agent workloads in both cloud and on-prem environments.
• Maintain the Sift MCP server to enable telemetry querying for AI tools.
• Create evaluation frameworks to track agent performance, cost, and latency.
• Integrate and test various frontier AI models.
• Design and implement data pipelines that process high-volume telemetry from rockets and satellites.
• Optimize queries and storage formats for time-series data to improve query performance and reduce costs.
• Work with product managers to define the roadmap for backend capabilities and reliability improvements.
• Implement monitoring and alerting to ensure system health and quick detection of anomalies.
• Write clean, maintainable code that adheres to strict engineering standards and security practices.
• Conduct code reviews and provide technical guidance to junior engineers on the team.
• Participate in on-call rotations to support production incidents and resolve critical issues.

Requirements

• Minimum of 3 years of professional software engineering experience.
• Proficiency in building backend services and APIs using languages such as Go, Python, or Rust.
• Understanding of distributed systems architecture.
• Experience with product ownership, including direct customer interaction and end-to-end delivery.
• Active interest in the current AI landscape and agentic workflows.
• Must be a U.S. citizen, lawful permanent resident, or protected individual to comply with ITAR and EAR regulations.
• Strong problem-solving skills and the ability to debug complex issues in distributed systems.
• Experience with version control systems, specifically Git, for managing large codebases.
• Ability to communicate effectively with both technical and non-technical stakeholders.
• Willingness to learn new technologies and adapt to changing project requirements.
• Commitment to writing tests and ensuring code quality throughout the development lifecycle.
• Capability to work independently and as part of a collaborative team in a fast-paced environment.
• Understanding of security best practices for handling sensitive data in regulated industries.

Nice to have

• Experience shipping LLM-powered features or agentic systems with multi-step planning.
• Background in time-series data, scientific computing, or hardware telemetry.
• Expertise in sandboxed execution environments.
• Practical knowledge of production Kubernetes, observability, and incident response.
• Familiarity with streaming data technologies like Kafka, Flink, or TimescaleDB.
• Experience designing tool ecosystems such as MCP.
• Contributions to open-source projects related to data infrastructure or AI agents.
• Experience with cloud provider services such as AWS, GCP, or Azure.
• Knowledge of data compression techniques for large datasets.
• Familiarity with hardware simulation tools and workflows.

Practical notes

The team works in person on Mondays and Thursdays in Marina Del Rey, with an additional full week of collaboration every two months. Candidates may work from the San Francisco office or relocate to the Los Angeles area.