Software Engineer, Applied AI

About the role

Sobek AI is building secure AI infrastructure for agentic workflows in life-sciences innovation networks and intergovernmental emergency response. Backed by $10M+ in funding and grants, we work with global, high impact partners on distributed workflows where reliability, security, and trust matter from day one. Our systems are already deployed in mission-critical customer environments. We're hiring a software engineer to help build the production systems behind Sobek’s core offerings. The work sits where AI powered workflows meet backend services, enterprise data, observability, and product surfaces. This is a foundational role on the engineering team.

Responsibilities

• Build AI powered workflows over enterprise and government data, with clear rules for what a model can see, what tools it can call, and when a human needs to review or approve an action.
• Design and ship services, data workflows, permissioning, and orchestration components that multiple Sobek products rely on.
• Build systems that operate over sensitive data with clear access boundaries, auditability, and predictable performance.
• Build evals and feedback loops for model behavior and workflow outcomes.
• Build systems that turn domain specific AI behavior into product infrastructure rather than one off customer logic.
• Write clean, maintainable code and create clear abstractions.
• Use tools like Claude Code, Codex, and similar systems to move faster, while applying the same standards to generated code as hand written code.

Requirements

• You have a track record of shipping production software used by real customers, and you have hands on experience building AI or LLM-powered systems beyond demos.
• Ideally, you’ve shipped at least one AI product or workflow used by real users.
• You have strong software fundamentals and are fluent in Python and/or TypeScript.

Qualifications

• Our current stack spans React/TypeScript, Python services, gRPC, AWS, Kubernetes, Terraform, Snowflake, and Docker; exact stack match is less important than range and judgment.
• Strong candidates may also have:
• Shipped production LLM or agentic workflows at an AI native startup, scaled AI product company, or serious applied-AI team;
• Built evals or feedback loops that caught real regressions;
• Debugged production failures in agent workflows, especially around grounding, tool use, or model/runtime boundaries;
• Built systems that operate over enterprise data with defined security boundaries;
• Worked in domains where wrong answers have serious consequences, such as scientific, medical, legal, financial, or public sector workflows;
• Owned meaningful product or platform surface area earlier than your title would suggest.

Skills

• Fluent in Python and/or TypeScript.
• Experience with React/TypeScript, Python services, gRPC, AWS, Kubernetes, Terraform, Snowflake, and Docker.

Benefits

• Company-paid health coverage (including dependents).
• Equity: Meaningful ownership for early engineers, with flexibility to extend for exceptional scope and impact.

Pay

$170 K – $230 K

Schedule

Hybrid (Seattle, WA)