AI Software Engineer

Job Summary

As an Sr Engineer on the AI Enablement team, you will be a hands-on builder and a force multiplier for how the broader Keystone engineering org works with AI. You'll split your time between scaling engineering practice and shipping autonomous agents that do real work — not prototypes that stall after a demo. 

This role requires strong software engineering fundamentals, comfort operating with ambiguity on a fast-moving small team, and the judgment to know when an AI-generated answer is good enough to ship versus a production risk. 

Job Responsibilities

• Scale engineering with AI 


• Drive spec-driven, agentic-IDE development workflows (Cursor, Claude Code) across the team, from spec to implementation to review, so AI usage translates into measurable velocity, not just novelty. 


• Define and evolve quality gates for AI-generated code: what changes in review, CI, and merge criteria when a large share of PRs are AI-assisted. 


• Build and maintain shared skills, prompts, and MCP tooling that other Keystone engineers reuse, reducing redundant AI infrastructure across teams. 


• Build production AI agents on the enterprise stack 


• Design and ship agent workflows (planner vs. fixed-workflow, state/retries, human-in-the-loop checkpoints) that automate real toil 


• Build well-scoped MCP tools/integrations against enterprise systems  with clear schemas, auth boundaries, idempotency, and explicit rules on what data never reaches the model. 


• Own evals and guardrails for agents in production: offline golden sets, online sampling, canary/rollback paths, and hard checks on numeric/PII/outbound-send correctness — distinguishing tool failures from model failures. 


• Design for operational readiness from day one: what breaks under a 10× usage spike before quarter close, what the kill switch looks like when an agent gets a fact wrong, and how incidents get triaged. 

Job Requirements

• Bachelor's degree in Computer Science, Engineering, or a related field; or equivalent, relevant experience. 


• 8+ years of professional software development experience, with proven ownership of at least one system or domain end-to-end. 


• Production experience with LLMs - prompt engineering, agent development, and evaluation frameworks. 


• Hands-on experience building agent harnesses: tool calling, state/session management, retries, guardrails, and stop conditions for long-running agent workflows. 


• Deep, hands-on proficiency in Python/Go/Java 


• Experience with agent/orchestration frameworks (LangChain, LangGraph, or equivalent) and MCP or similar tool-calling standards, integrated with enterprise systems 


• Working knowledge of AI-native, spec-driven development workflows (agentic IDEs like Cursor/Claude Code) and defining quality gates for AI-generated code. 


• Strong problem decomposition and stakeholder navigation - able to scope an ambiguous cross-functional ask into a shippable plan and own it end-to-end, forward-deployed-engineer style. 

Education