Note: The job is a remote job and is open to candidates in USA. Implentio is building the intelligence layer for modern ecommerce operations. They are seeking a Full-Stack Engineer, AI & Automation to design and ship AI-powered features, build automation, and integrate AI into their products.
Responsibilities
- Build and ship AI products. Design, develop, and deliver agentic features end-to-end, including chat-based interfaces, agent workflow experiences, and internal copilots that serve real users in production
- Leverage agentic coding workflows. Use modern agentic coding tools daily, including Claude Code, Codex, Cursor, and similar assistants, to accelerate delivery while maintaining high code quality and engineering standards
- Design agent systems. Architect agent internals, including tool calling, multi-step orchestration, memory and state management, retrieval pipelines, permissions models, and failure recovery strategies
- Own evals and quality. Build and maintain agent evaluation infrastructure, including regression suites, scenario-based tests, golden traces, and both offline and online metrics, so you always know whether your agent got better or worse
- Implement observability. Instrument agents with production-grade observability, including distributed tracing, prompt and version tracking, tool-call telemetry, and cost and latency monitoring
- Own production readiness. Take responsibility for the full lifecycle, including rollout plans, QA, guardrails, incident response, and continuous improvement of deployed agents
Skills
- Proficiency in TypeScript/Node.js and/or Python, with experience in modern web stacks and startup-pace delivery
- Proven full-stack engineering ability. You have shipped production software end-to-end, not just prototypes or demos
- Shipped LLM-powered features to production. You have owned at least 1 to 2 agentic features or products from design, build, deployment, and operation
- Familiarity with agentic coding best practices. You understand task decomposition, agent delegation, prompt hygiene, iterative loops, and how to review and steer agentic outputs effectively
- Practical experience with agent evals and tracing
- Solid engineering fundamentals. Testing, debugging, performance optimization, and reliability are second nature to you
- Familiarity with agent tooling ecosystems, including prompt and version stores, eval harnesses, and tracing and telemetry platforms such as OpenTelemetry, LangSmith, Datadog, Honeycomb, or similar
- Experience with RAG architectures, including vector databases, indexing strategies, chunking approaches, and retrieval evaluation
Company Overview