Job Description

We're building an agentic AI platform that helps enterprises transform complex business workflows into AI-powered operations. We work with leading global companies to identify high-value workflows, deploy AI agents into real business environments, and help organizations move from experimentation to measurable enterprise impact.

We believe AI adoption inside the enterprise isn't just a technology challenge. It requires business context, workflow understanding, change management, trust, ownership, and a clear path to value. That's where this role comes in.

We are a well-funded, early-stage startup looking for a talented and motivated Backend Engineer specializing in infrastructure to join our founding team. The focus of this role is to build and scale the infrastructure that powers autonomous AI agents automating complex enterprise workflows. You will own the systems, pipelines, and platforms that let our AI agents run reliably, securely, and at scale in production.

Your Impact

Infrastructure & Platform

• Design, build, and own the core infrastructure powering our AI agent platform, from data pipelines to production deployment systems.
• Build and scale the backend systems that support high-throughput document processing and data extraction workloads.

Cloud Infrastructure and Scalability

• Architect and deploy infrastructure on cloud platforms (AWS, GCP, or Azure) with a focus on scalability, reliability, and cost efficiency.
• Own containerization and orchestration (Docker, Kubernetes) for all production workloads.
• Build and maintain CI/CD pipelines and DevOps practices that let the team ship fast without breaking things.

Data Infrastructure

• Design and manage data pipelines to process and analyze large volumes of documents and unstructured data at scale.
• Build the infrastructure layer connecting AI agents to databases, vector stores, and enterprise systems (ERP, CRM).

API & Systems Integration

• Build and maintain robust, well-documented APIs connecting AI agents with external systems and enterprise software.
• Design for reliability: retries, observability, and graceful degradation across distributed systems.

Security and Compliance

• Implement authentication and authorization mechanisms (OAuth2, JWT) to secure AI-driven systems.
• Ensure compliance with data privacy standards (e.g. GDPR, HIPAA) and drive best practices for secure data handling across the infrastructure.

Monitoring and Optimization

• Build observability and monitoring systems to track infrastructure health, performance, and cost.
• Continuously optimize system performance for speed, reliability, and cost-efficiency at scale.

Collaboration

• Work closely with AI/ML engineers, product, and the founding team to make sure infrastructure decisions support fast iteration and production-grade reliability.
• Participate in code reviews, design discussions, and architecture planning to drive infrastructure strategy.

Requirements

What It Takes

Experience

• 5+ years of experience in backend or infrastructure engineering, ideally supporting production AI/ML systems or high-throughput data pipelines.
• Proven track record of building and scaling infrastructure in production environments.

Technical Skills

• Proficiency in Python.
• Databases: Proficiency in SQL (PostgreSQL, MySQL) and NoSQL (e.g. Document DB, Vector DB).
• Cloud: Deep experience deploying and scaling large production applications on AWS, GCP, or Azure.
• Containerization and orchestration: Docker, Kubernetes.
• Security: Strong understanding of OAuth2, JWT, and best practices for securing distributed systems.

Nice To Have

• Experience with RPA (Robotic Process Automation) tools.
• Familiarity with graph databases (Neo4j) for managing complex workflows.
• Familiarity with Go and Rust.
• Experience working alongside AI/ML teams using frameworks like TensorFlow, PyTorch, or Hugging Face.