Daily, practical use of AI coding tools and agent frameworks; building LLM-backed features and evaluation pipelines as core parts of the workflow.
About the Role
Senior Software Engineer to design, build, and operate production services while integrating AI and agent frameworks as core development collaborators; responsible for shipping scalable systems, raising code quality, and mentoring engineers on AI-native practices and judgment.
Job Description
Role
We are hiring a Senior Software Engineer to build and scale a production platform where AI tools and agent frameworks are core development collaborators. You will design architectures, ship production services, integrate AI-powered features, and help define standards for safely incorporating AI output into the codebase.
Key Responsibilities
- Design, build, and operate production services across backend, infrastructure, and integration layers.
- Lead technical projects from ambiguity to shipped feature: scope, design, build, deploy, measure, and iterate.
- Use AI coding tools (e.g., Claude Code, Copilot, Cursor) as force multipliers for drafting, refactoring, exploring, and reviewing code while remaining accountable for shipped work.
- Build and integrate AI-powered features such as agent workflows, LLM-backed APIs, retrieval systems, and evaluation pipelines.
- Perform rigorous code review, including reviewing AI-generated code and establishing safe incorporation standards.
- Debug complex production issues, trace unfamiliar systems, form hypotheses, and fix root causes.
- Mentor engineers on judgment, verification, and effective use of AI in engineering workflows.
- Contribute to architectural decisions and long-term technical strategy.
Requirements
Core engineering skills
- 7+ years of professional software engineering experience building and operating production systems.
- Strong fundamentals in data structures, concurrency, distributed systems, databases, networking, and security.
- Production sense: scalability, observability, safe rollouts, and incident debugging.
- Excellent code review judgment and the ability to spot subtle bugs, security holes, and architectural issues.
- Clear technical writing: produce design docs and explain complex problems in plain language.
AI-native engineering practices
- Fluent daily use of AI coding tools, with judgment about when to delegate, verify, or write code manually.
- Experience with LLM-backed systems: agent frameworks (e.g., LangGraph, AutoGen), tool/function calling, RAG pipelines, prompt evaluation, or model fine-tuning.
- Understanding of LLM and agent failure modes (hallucination, drift, prompt injection, latency and cost issues) and operational mitigations.
- Evaluation mindset: measure model/agent quality with concrete metrics and use eval harnesses, regression suites, or human-in-the-loop processes.
Judgment and collaboration
- Strong sense of ownership for shipped code, regardless of origin.
- Good taste in design, ability to balance engineering trade-offs and manage tech debt.
- Clear communication to translate fuzzy product requirements into concrete specs.
- Track record or interest in mentoring others on new AI-era engineering skills.
Nice to have
- Experience building or operating multi-step production agent systems with feedback loops.
- Contributions to open-source AI tooling or agent frameworks.
- Experience in EdTech or prior technical leadership/mentorship beyond individual contributions.