Staff Software Engineer

Quick Facts

• Forward-deployed engineer role focused on building working software for real business problems.
• Work closely with internal lines of business to drive AI adoption and ship production AI applications.

Description

Compression of the distance between “we need something that does X” and “here, try this.”

You work directly with internal stakeholders to design and build systems end to end based on real pain points, workflows, and the current technical landscape. Discovery is part of engineering: you sit with users, watch them work, ask questions, and translate findings into something buildable. You iterate quickly by building during conversations, turning messy inputs (spreadsheets, PDFs, screenshots, recorded calls, half-written documents, contradictory emails) into coherent, shippable software.

You ship production AI applications on top of frontier LLMs, agents, MCP servers, evaluation harnesses, retrieval systems, and custom skills. You evaluate what you build (not just demo it), iterate fast across multiple cycles where requirements shift, and own the full stack (frontend, backend, data, integrations, deployment, and observability) with no handoff.

When patterns repeat, you codify what works—prompt structures, evaluation harnesses, integration shims, agent templates—so other engineers can reuse them. You also maintain an ongoing relationship over the lifecycle of engagements, identifying new opportunities and hardening prototypes into production.

Responsibilities

• Work where the problem is: collaborate with stakeholders to understand workflows, pain points, data, and architecture.
• Conduct real discovery with users while continuing to engineer; convert feedback into buildable requirements.
• Build initial versions quickly during conversations to get feedback on working software.
• Turn messy, conflicting inputs into coherent solutions without requiring prior cleanup.
• Ship production LLM/agent-based applications using evaluation and retrieval, running against real workflows.
• Iterate across engagements and keep shipping despite shifting requirements.
• Own full stack delivery end to end: UI, backend, data, integrations, deployment, and observability.
• Codify reusable patterns and push them back to the platform/engineering teams.
• Stay engaged through the lifecycle to harden and productionize outcomes.

Requirements

• 8+ years of full-stack engineering experience with meaningful time shipping production systems end to end.
• Background as a technical founder, forward deployed engineer, or software engineer with consulting experience.
• Strong CS fundamentals: data structures, algorithms, and system design; can whiteboard service architecture and discuss tradeoffs.
• Frontend depth: modern React, TypeScript, component architecture, state management, and ability to build polished UI.
• Backend depth (in priority order): Node.js, Java, Python; API design, data modeling, auth, error handling; comfortable owning a service from request handler to schema.
• Production LLM experience: prompt engineering, agent development, evaluation frameworks, retrieval, and deployment at scale; shipped at least one real LLM-backed application used by others.
• Fluency with AI-assisted development tools and agentic coding; can demonstrate a process that delivers measurable results.
• Data fluency: databases at a real working level and comfort with Python data tooling.
• Cloud and deployment fluency: AWS/GCP/Azure; can deploy a service behind real auth; CI/CD, containers, and observability.
• Integration experience: systems outside what you built; SSO, OAuth, third-party APIs, internal platforms, legacy databases.
• High agency to navigate ambiguity and make/own decisions.
• High cooperation and low ego; ability to collaborate across team lines.
• Communication skills: can address both executive and engineering audiences and translate end-user problems into buildable work.
• Stay current with LLM capability changes, agent patterns, and AI product stacks.
• Bachelor’s degree in Computer Science or equivalent combination of education, training, and professional experience.

Benefits

• Opportunity to embed with strategic business lines and drive AI adoption by shipping working software against real problems.
• High ownership: end-to-end responsibility across the full stack, including production observability.
• Fast iteration cadence with repeated cycles of building, evaluation, and shipping.
• Ability to codify reusable engineering patterns to improve the broader platform.