AI Application Architect
AI Application Architect
Posted 47 days ago
SENIORITY
Lead
About the role
- Define architecture for AI-native applications including agentic systems, RAG pipelines, multi-model inference layers, and human-in-the-loop workflows
- Drive infrastructure decisions for scalable AI workloads: vector databases (Turbopuffer, pgvector, Milvus), workflow orchestration (Temporal, Airflow), and async compute patterns
- Design and govern the integration layer between LLMs (OpenAI, Anthropic, Gemini, open-source) and backend services, including prompt management, context window optimization, and cost governance
- Lead LLMOps and observability strategy — tracing (OpenTelemetry), evaluation pipelines, prompt versioning, drift detection, and integration with platforms like Langfuse or Arize
- Establish security and compliance posture for AI systems — SSRF/injection hardening, LLM guardrails, data residency, and supply chain security for model artifacts and dependencies
- Partner with product and research to evaluate emerging AI capabilities and determine when/how to adopt them (e.g., reasoning models, multimodal, fine-tuning, RLHF)
- Champion engineering standards — API design, schema governance, testing strategies, and architecture decision records (ADRs)
- Mentor senior engineers and establish guild-level technical communities around AI platform topics
- 10+ years of software engineering with 5+ years in a principal/staff or architect-level role
- Hands-on experience designing and shipping production LLM-powered applications (not just prototypes)
- Experience shipping complex, user-facing application platforms — particularly in SaaS, productivity tools, or enterprise software.
- Demonstrated ability to lead full-stack teams building rich web application experiences (React, TypeScript/Node.js, modern frontend architectures) with strong backend (Python) and API design sensibility
- Experience with MCP (Model Context Protocol) or comparable tool-calling/plugin infrastructure
- Familiarity with workflow orchestration engines (Temporal, Prefect) for long-running AI tasks
- Exposure to LLM evaluation frameworks (automated judging, red-teaming, regression suites)
- Background in developer-facing products or internal AI platforms / AI coding tooling
- Understanding of supply chain security for ML models (artifact signing, registry enforcement, SBOM)
- Contributions to open-source AI tooling or published architectural writing
Before you apply
Applying takes about a minute. These four things decide how fast it moves after that.
Your profile is current
It's what we read first. Occupations, seniority and locations matter more than a long history.
Two examples you can talk through
Not a portfolio — just two pieces of work where you can explain the decisions and what you'd change.
A number in mind
What you're on now and what would make you move. We negotiate better when we know both.
Your notice period
Employers plan around it, and it's the question that stalls offers most often.
Once you apply, someone reads it and calls you before anything reaches the employer — usually within two working days.
