Agentic Software Engineer (Full Stack)
S
SpecrightAI software
Location: Egypt
Workplace: RemoteFull-Time
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Required Skills
- Node.jsPythonTypeScript
Requirements
- Demonstrated full-stack engineering ability and experience shipping production software end-to-end.
- Hands-on experience building LLM-powered agents for production.
- Have owned at least 1–2 agentic features or products through deployment and operation.
- Understand agentic coding practices, including task decomposition, agent delegation, prompt hygiene, iterative loops, and reviewing and steering agentic outputs.
- Have practical experience building agent evaluation systems, including trace-based debugging and regression detection.
- Bring strong engineering fundamentals in testing, debugging, security, performance optimization, and reliability.
- Nice to have: proficiency in TypeScript/Node.js and/or Python, and experience with modern web stacks.
- Nice to have: familiarity with prompt/version stores, evaluation harnesses, and tracing or telemetry platforms such as OpenTelemetry, LangSmith, Datadog, or Honeycomb.
- Nice to have: experience with RAG architectures, vector databases, indexing, chunking, and retrieval evaluation.
- Nice to have: experience designing agent tool APIs, including structured output schemas, idempotency, rate limiting, and error handling.
Responsibilities
- Build and deliver production agentic applications, including chat-based interfaces, AI workflow tools, and internal copilots.
- Use agentic coding tools such as Claude Code, Codex, and Cursor while maintaining code quality and engineering standards.
- Design agent systems for tool calling, multi-step orchestration, memory and state management, retrieval, permissions, and failure recovery.
- Build and maintain evaluation infrastructure, including regression suites, scenario-based tests, golden traces, and offline and online metrics.
- Instrument agents with distributed tracing, prompt and version tracking, tool-call telemetry, and cost and latency monitoring.
- Own rollout plans, QA, guardrails, incident response, and continuous improvement for deployed agents.
View Full Description & ApplyYou'll be redirected to the employer's site