Standard Template Labs is a stealth-mode, AI-native startup reimagining the future of IT Service and Configuration Management. They are seeking a Principal Software Engineer to own the technical vision for AI design and implementation across their platform, focusing on building production AI systems and mentoring engineers.
Responsibilities:
- Architect the core intelligence layer of the platform, spanning data ingestion, embeddings, retrieval, graph reasoning, agents, and real-time inference
- Define how LLMs and predictive models integrate across backend services, APIs, and user-facing experiences
- Identify high-impact opportunities where generative, predictive, or autonomous AI can eliminate operational toil, improve system understanding, or enhance decision-making
- Lead architectural decisions around model selection, evaluation, fine-tuning, and inference infrastructure (custom vs OSS vs managed APIs)
- Establish best practices for AI-first engineering, including prompt and schema design, context assembly, evaluators, guardrails, observability, and continuous model monitoring
- Partner with product and leadership to align AI capabilities with customer outcomes, trust requirements, and long-term platform strategy
- Build end-to-end AI-powered features - from backend reasoning services to APIs and user-facing workflows
- Design and implement production-grade LLM and agent workflows, including automated enrichment, anomaly explanation, topology discovery, change impact analysis, and natural language querying
- Develop scalable backend systems for high-throughput inference, embedding generation, vector search, and graph traversal
- Collaborate on or directly contribute to frontend experiences that make AI outputs understandable, actionable, and debuggable for users (e.g., explanations, confidence signals, provenance, and feedback loops)
- Implement retrieval-augmented generation (RAG) pipelines and hybrid search systems that combine structured data, graphs, and unstructured context
- Write clean, well-structured, production-quality code—and champion AI-assisted development tools (Claude, Cursor, Windsurf, etc.) to improve velocity and correctness
- Continuously evaluate emerging AI frameworks, agent runtimes, orchestration tools, and model APIs, integrating them where they drive real user value
- Design data models and pipelines that support learning, reasoning, and traceability across the platform
- Build and evolve distributed systems that are observable, fault-tolerant, and cost-efficient under AI workloads
- Partner with infrastructure and DevOps teams to shape deployment, scaling, monitoring, and rollback strategies for AI-driven services
- Ensure AI systems meet enterprise requirements for reliability, security, explainability, and compliance
- Mentor engineers on full-stack AI patterns, system design for AI workloads, and practical approaches to shipping intelligent features
- Lead architecture reviews and technical deep-dives focused on reliability, safety, performance, and user trust
- Influence engineering standards and culture, emphasizing craftsmanship, clarity, and ownership across the stack
- Help attract and develop top-tier engineering talent excited about AI-native, product-driven systems