Staff AI Architect

About TextLayer

TextLayer helps enterprises and funded startups deploy advanced AI systems without rewriting their infrastructure. We work with organizations across fintech, healthtech, and other sectors to bridge the gap between AI potential and practical implementation.

Our approach combines deep technical expertise with proven frameworks like TextLayer Core to accelerate development and ensure production-ready results. From bespoke AI workflows to agentic systems, we help clients adopt AI that actually works in their existing tech stacks.

We're on a mission to help address the implementation gap that over 85% of enterprise clients experience in adding AI to their operations and products. We're looking for sharp, curious people who want to meaningfully shape how we build, operate, and deliver.

If you're excited to work on foundational AI infrastructure, solve complex problems for diverse clients, and help define what agentic software looks like in practice, we'd love to meet you.

The Role

• The AI Architect plays a critical role in our team. Working on both the frontend and backend architecture and orchestration layer for our AI systems, including retrieval-augmented generation systems, agentic systems, and tool integrations.

Key Responsibilities

• Architect and maintain Python-based services using FastAPI for internal and customer-facing AI use cases

• Build and scale secure, well-structured API endpoints that interface with LLMs, vector stores, and agentic tools

• Implement orchestration logic and tool chaining for advanced agent workflows

• Optimize service performance and latency across AI infrastructure layers

• Collaborate with frontend, AI, and devops teams to ensure system-wide reliability and observability

• Set up robust test coverage and CI pipelines for backend services

• Contribute to our modular architecture for tool-based reasoning agents

• Stay current with emerging trends in AI engineering, LLM integrations, and scalable backend systems

• Drive technical strategy and roadmap for AI infrastructure

• Mentor and guide senior and mid-level engineers on architecture and best practices

What You Will Bring

• To succeed in this role, you’ll need deep full-stack development expertise, a strong understanding of modern architecture patterns, and a bias toward building modular, maintainable systems.

Required Qualifications

• 8+ years of experience as a full-stack engineer, with at least 3 years building scalable backend systems in Python

• Strong knowledge of Flask or FastAPI for building and scaling production grade APIs

• Experience with LLM orchestration frameworks (e.g., LiteLLM) and integrating OpenAI/Anthropic APIs

• Familiarity with vector databases, embeddings, and RAG patterns

• Experience building and maintaining infrastructure that integrates with frontends, CLIs, and external APIs

• Comfortable with GitHub, Docker, and CI/CD tooling (e.g., GitHub Actions)

• Proficiency in writing robust, tested, and well-documented backend code

• Track record of leading technical initiatives and influencing architecture across teams

Bonus Points

• Familiarity with AWS/GCP/Azure at scale

• Experience with Langfuse or similar observability/tracing tools

• Have built your own agentic end-to-end system

• Experience mentoring engineers and driving technical standards

• Background in designing multi-tenant or platform-level AI infrastructure

• Experience presenting technical designs to leadership or clients

• Contributions to open-source AI/ML projects

Don't Meet These?

We hire for great developers - not just those with extensive backgrounds in AI. If you've held Staff or Principal roles within your organization and want to learn AI, we want to meet you!