Software Infrastructure Developer (AI Focus)

BioCatch is the leader in Behavioral Biometrics - a technology that leverages machine learning to analyze an online user's physical and cognitive digital behavior to protect individuals online. Our mission is to unlock the power of behavior and deliver actionable insights to create a digital world where identity, trust, and ease coexist.

Today, 34 of the world's largest 100 banks and 210 total financial institutions rely on BioCatch Connect™ to combat fraud, facilitate digital transformation, and grow customer relationships. BioCatch's Client Innovation Board - an industry-led initiative including American Express, Barclays, Citi Ventures, and National Australia Bank - helps us identify creative and cutting-edge ways to leverage the unique attributes of behavior for fraud prevention. With over a decade of analyzing data, more than 80 registered patents, and unparalleled experience, BioCatch continues to innovate to solve tomorrow's problems.

For more information, visit www.biocatch.com.

We are looking for a proactive and skilled Software Infrastructure Developer with a strong AI focus to join our team. In this role, you will design and build the infrastructure, tooling, and AI-powered automation that keep our engineering systems reliable, scalable, and intelligent.

You will be responsible for embedding GenAI and agentic capabilities into our internal developer platforms and CI/CD workflows - creating frameworks, libraries, and multi-agent systems that accelerate automation, improve system stability, and unlock new levels of engineering productivity. This is a hands-on role for someone who thrives at the intersection of infrastructure engineering and applied AI.

The ideal candidate brings deep technical expertise in Python (FastAPI) and/or TypeScript, Kubernetes, CI/CD (Jenkins, GitHub Actions), containerization, and cloud infrastructure - combined with hands-on experience building LLM-powered applications, agents, MCP servers, and RAG pipelines.

What you'll be doing:

• AI-Powered Infrastructure Design: Architect, build, and maintain scalable infrastructure and frameworks on Kubernetes that integrate GenAI and agentic workflows into engineering systems, ensuring reliability and consistency at scale.
• AI Tooling & Library Development: Design, build, and scale AI agents, reusable libraries, SDKs, and MCP servers that simplify end-to-end automation and empower engineering teams to adopt AI capabilities in their daily workflows.
• Intelligent CI/CD Integration: Integrate, optimize, and augment CI/CD pipelines using Jenkins and GitHub Actions - augmenting them with AI-driven automation to streamline deployment, testing, and operational workflows.
• Agentic Automation: Design and implement multi-agent systems and LLM-powered workflows that automate complex engineering and operational tasks - from planning and tool selection to execution and human-in-the-loop approval.
• End-to-End Feature Ownership: Own new AI-driven features and platform capabilities from design through production, ensuring high-quality, reliable, and observable releases.
• Cross-Functional Collaboration: Partner with engineering, product, and business teams to identify high-impact opportunities for AI-driven automation and translate operational needs into scalable technical solutions.
• AI Observability & Governance: Implement observability, evaluation, and governance practices for AI systems - including tracing, prompt/tool-call logging, latency, token consumption, cost tracking, and quality evaluation.
• Documentation & Enablement: Document best practices, patterns, and usage guidelines for AI tools and libraries to accelerate adoption and knowledge sharing across the organization.
• Technology Research & Innovation: Continuously evaluate emerging AI, GenAI, and cloud-infrastructure technologies and champion their adoption to maximize platform impact.

Requirements

Core Engineering

• Experience: Minimum of 3 years hands-on experience with Python and/or TypeScript.
• AI Experience: Minimum of 2 years of hands-on experience designing and building agentic AI systems, LLM-powered applications, or multi-agent workflows in production environments.
• Backend Frameworks: Hands-on experience building backend services with FastAPI (or equivalent modern Python web framework) - including async patterns, dependency injection, and API design.
• Programming Skills: Strong grasp of software development principles - writing clean, maintainable, testable, and scalable code.
• Backend & Cloud Infrastructure: Proven experience building backend systems and cloud infrastructure at scale.

Infrastructure & DevOps

• Kubernetes: Hands-on experience deploying, operating, and troubleshooting workloads on Kubernetes - including networking, resource management, autoscaling, and debugging cluster-level issues.
• Helm: Strong experience authoring and maintaining Helm charts - templating, values management, chart dependencies, versioning, and release lifecycle.
• Containerization: Deep hands-on experience with Docker - writing efficient, secure, multi-stage builds and managing container lifecycles.
• CI/CD: Proven experience designing and managing CI/CD pipelines with Jenkins and GitHub Actions in cloud environments (AWS / Azure).
• Cloud Platforms: Practical experience with AWS and/or Azure - compute, networking, IAM, and managed services.
• Infrastructure as Code: Familiarity with IaC principles and GitOps workflows.

AI / GenAI (Mandatory)

• AI Platform Development: Hands-on experience building AI platforms and backend systems that power LLM-based applications.
• Agent Architecture: Deep understanding of agent design - planning, tool selection, state management, short- and long-term memory, retries, fallbacks, and human-in-the-loop approval flows.
• Multi-Agent Systems: Experience designing and building multi-agent workflows where specialized agents collaborate, delegate tasks, and exchange structured information across defined protocols.
• Frameworks & LLM APIs: Hands-on experience with LangChain, LangGraph, and LLM APIs such as OpenAI and Anthropic - including prompt engineering, tool/function calling, and structured outputs.
• MCP (Model Context Protocol): Hands-on experience building and integrating MCP servers and clients to expose tools, resources, and context to LLM-powered agents in a standardized way.
• RAG & Context Engineering: Practical experience building Retrieval-Augmented Generation pipelines - embeddings, vector stores, chunking strategies, retrieval quality tuning, and context-window optimization.
• Agent Orchestration: Hands-on knowledge of orchestrating multi-step, multi-agent workflows with reliable state management and error recovery.
• AI Observability: Experience implementing observability for AI systems - traces, prompt/response logging, tool-call inspection, retrieval results, latency, token consumption, error rates, and cost tracking.
• AI Evaluation & Governance: Understanding of evaluation frameworks (offline/online eval, regression testing for prompts and agents), guardrails, and responsible-AI governance practices.
• Internal Platform Building: Proven ability to build reusable internal platforms and SDKs that improve developer productivity and accelerate AI adoption across engineering teams.

Ways of Working

• Version Control: Strong Git fundamentals - branching strategies, code review, and collaborative workflows.
• Problem-Solving: Excellent analytical and troubleshooting skills across distributed systems, cloud infra, and AI pipelines.
• Collaboration: Ability to work with engineering and business stakeholders and translate operational needs into scalable technical platform solutions.
• Adaptability: Thrives in a fast-paced environment and rapidly adopts new tools, frameworks, and technologies.