About TextLayer
TextLayer helps enterprises and funded startups build, deploy, and scale advanced AI systems, without rewriting their infrastructure.
We provide engineering teams with a modular, stable foundation, so they can adopt AI without betting on the wrong tech. Our flagship stack, TextLayer Core, is maintainable, tailored to the environment, and deployed with Terraform and standardized APIs.
We’re a team 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, ship production-grade systems quickly, and help define what agentic software looks like in practice, we’d love to meet you.
The Role
The AI Engineer plays a critical role in our team, working on both the frontend and backend architecture and orchestration layer for our AI systems. You'll build production-grade RAG (Retrieval-Augmented Generation) pipelines, develop sophisticated AI Agent workflows, and create robust LLM integrations that power our customer-facing applications.
Key Responsibilities
Architect and maintain Python-based services using Flask and modern AI frameworks for RAG and Agent implementations
Build and scale secure, well-structured API endpoints that interface with LLMs (OpenAI, Hugging Face models), vector databases, and agentic tools
Implement advanced Agent orchestration logic, prompt engineering strategies, and tool chaining for complex AI workflows
Design and optimize RAG pipelines, including data loaders, chunking strategies, vector embeddings, and search integration with Elasticsearch/OpenSearch
Develop and maintain ML pipelines for processing, indexing, and retrieving data in vector stores
Build seamless frontend experiences using Next.js, Vercel AI SDK, and modern React patterns for streaming LLM responses
Containerize AI services using Docker and implement scalable deployment strategies with AWS ECS/Lambda
Collaborate with AI research teams to productionize PyTorch models and Hugging Face transformers
Optimize prompt engineering techniques for improved LLM performance and reliability using Langfuse observability
Set up robust test coverage, monitoring, and CI/CD pipelines for AI-powered services using GitHub Actions
Stay current with emerging trends in AI engineering, Agent architectures, and RAG systems
What You Will Bring
To succeed in this role, you'll need deep full-stack development expertise, hands-on experience with LLM and RAG implementations, and a strong understanding of modern AI Agent patterns. You should be passionate about prompt engineering and building scalable AI pipelines.
Required Qualifications
3+ years of experience as a full-stack engineer with strong Python expertise
Hands-on experience building RAG systems and AI Agent architectures in production
Proficiency with LLM orchestration frameworks and AI development tools
Experience with vector databases, embeddings, and vector search implementations
Strong knowledge of prompt engineering principles and LLM optimization techniques
Experience integrating OpenAI APIs, Hugging Face models, or similar LLM providers via LiteLLM
Proficiency with Docker for containerizing AI applications
Experience building ML/data pipelines for AI systems
Comfortable with modern AI tooling and search technologies like Elasticsearch/OpenSearch
Track record of building end-to-end Agent systems with RAG capabilities
Bonus Points
Experience with PyTorch for model deployment and optimization
Contributions to open-source AI/LLM projects
Experience with advanced prompt engineering and LLM fine-tuning
Familiarity with multiple vector database solutions
Background in implementing AI applications at scale
Experience with Hugging Face ecosystem and model deployment
Frontend development experience with Next.js, React, and Vercel AI SDK for streaming interfaces
Published research or blog posts on RAG, Agents, or LLM applications
AWS experience with ECS/Lambda for AI workload deployment
Experience with Langfuse for LLM observability and tracing
Document processing pipeline experience: ingestion from diverse sources (PDFs, documents, web content), text extraction, and chunking strategies
Infrastructure experience with Terraform, GitHub Actions, and production monitoring
Data engineering background: experience with orchestration tools for ML/AI workloads
Experience with async workflows and scalable data processing patterns
