Who We Are Provoke is a global consulting firm building AI-native solutions that transform how work gets done. Founded on a culture of innovation, growth, and curiosity, we partner with global clients to design and deploy agentic AI embedded directly into workflows so teams move faster, think smarter, and scale with purpose. What We Do We build bespoke software using modern technologies to help our clients solve complex business problems, achieve operational excellence, and flourish in an increasingly digital world. The Provoke Experience We are committed to building high-performing, diverse teams. We provide tangible rewards for effort, hybrid-first flexibility with purposeful in-person collaboration, and learning opportunities to fast-track your career. We focus on diversity in race, gender, orientation, and experience because we know diversity fuels innovation. The Opportunity We are seeking a Full-Stack Developer with strong DevOps and AI integration skills to build, deploy, and secure end-to-end applications for banking clients. This role requires expertise in modern web development, containerization, on-premises Docker environments, secure infrastructure (e.g., HashiCorp Vault), and AI/LLM-based architectures (including RAG pipelines). The ideal candidate will have hands-on technical expertise, strong security awareness, and the ability to communicate complex solutions to clients. Key Responsibilities Infrastructure & Server Setup Prepare hardware and configure Linux-based and Windows-based on-prem servers (small to medium complexity) Install, configure, and run Docker in on-premises environments, including Docker Compose for multi-service setups Deploy and configure Apache/Nginx within containerized environments Security & Secrets Management Deploy and configure HashiCorp Vault on premises (medium to large complexity) Set up secrets and certificates, enable encryption, and configure secure access Ensure client applications can securely pull secrets from Vault AI/LLM Integration Set up LLM environments (low to medium complexity) Build knowledge bases using vector databases (Postgres, Weaviate, or similar) Implement document ingestion pipelines (document parsing, chunking, embeddings generation, and storage) RAG (Retrieval-Augmented Generation) Orchestration Develop inference pipelines using LangChain or n8n Implement retrieval, augmentation, and generation workflows Create API contracts for frontend-backend integration Backend & API Development Initialize and build Python/FastAPI projects Expose RAG pipeline endpoints through secure REST APIs Frontend Development Create React SPA applications with chat-like UIs (ChatGPT-style interfaces) Integrate frontend with backend APIs based on defined contracts Deployment & Routing Configure Apache/Nginx reverse proxy rules for routing frontend and backend traffic Client Interaction Present technical solutions, architecture diagrams, and deployment strategies to clients Translate complex technical concepts into clear, non-technical language Collaborate with stakeholders to align solutions with business and security requirements Required Skills & Qualifications Technical Expertise Strong experience with Docker (on-premises), Linux server administration, and container orchestration Hands-on experience with HashiCorp Vault (secrets engines, policies, and client integrations) Proficiency in Python (FastAPI, Flask) and React.js Understanding of vector databases (Weaviate, Pinecone, or Chroma) and RAG pipelines Familiarity with LangChain or workflow automation tools like n8n Web servers: Nginx/Apache reverse proxy and SSL/TLS configuration Knowledge of document parsing (PDF, CSV, text) and embedding models (OpenAI, Hugging Face) Security Awareness Strong understanding of data security, encryption, and certificate management Awareness of banking security standards (e.g., SOC2, PCI-DSS basics) Ability to design and review secure APIs and infrastructure Soft Skills Excellent presentation skills for client demos and solution walkthroughs Ability to document and explain technical architectures clearly Collaborative mindset for cross-functional teamwork Nice-to-Have Skills Exposure to GPU-based LLM hosting (e.g., Hugging Face models) Familiarity with cloud services (AWS, GCP, Azure) and hybrid on-prem/cloud setups