Senior Full Stack Engineer

About the Role

We are seeking a Senior Full-Stack Engineer to join our team and help build the next generation of AI solutions. This is a unique opportunity to be a key technical contributor in a fast-paced, innovative environment where you'll wear many hats and have significant impact on our product and engineering culture.

As a full-stack engineer, you'll work across the entire technology stack—from backend services and data pipelines to infrastructure and deployment. You'll collaborate closely with the engineering team to architect, build, and scale our micro-services based platform while maintaining high code quality and operational excellence, utilising AI to maximise software development productivity.

About Prolo

Prolo is building an AI-powered procurement platform for the construction industry, which is one of the oldest and least digitised sectors in the world. The core system ingests unstructured purchase orders and transforms them into structured materials data, integrating with a network of suppliers and logistics partners to automate quoting, sourcing, and fulfilment workflows.

What We're Building

We're building a sophisticated AI platform that leverages graph databases, machine learning, and modern cloud infrastructure to deliver intelligent procurement and customer service solutions. Our stack includes:

• Backend Services: Python 3.13, FastAPI, async micro-services architecture
• Data Layer: Neo4j graph database, PostgreSQL, complex data modelling
• AI/ML: OpenAI integration, semantic search, conversational agents, unstructured data analysis and extraction
• Infrastructure: AWS (Lambda, ECS/EKS, API Gateway, S3)
• DevOps: Terraform, GitHub Actions, Helm, Infrastructure-as-Code
• Data Science: Graph analytics, data pipelines, ETL workflows, Jupyter notebooks

Required Qualifications

Software Development

• 5+ years of professional software engineering experience
• Strong proficiency in Python (3.10+) with deep understanding of async programming
• Experience with Poetry or similar Python dependency management tools
• Experience building RESTful APIs and micro-services
• Solid understanding of database design and optimisation (both SQL and NoSQL)
• Experience with graph databases (Neo4j preferred) or willingness to learn quickly
• Knowledge of event-driven architectures and message queues
• Knowledge of API design principles, data validation, and serialisation
• Experience with observability tools (OpenTelemetry, Prometheus, Grafana)
• Experience with AWS Lambda and serverless architectures
• Experience working across the stack (backend + some frontend)
• Understanding of web technologies, HTTP, and API integrations
• Ability to contribute to responsive frontend code when needed
• Hands-on experience using AI-assisted development tools (e.g. Cursor, GitHub Copilot) including prompt engineering, context management, and evaluating AI-generated code critically
• Familiarity with agentic coding workflows — using AI agents to scaffold, refactor, test, and document code autonomously

DevOps & Infrastructure

• Hands-on experience with cloud platforms (AWS preferred)
• Experience with containerisation (Docker) and orchestration (Kubernetes)
• Knowledge of Infrastructure as Code (Terraform, CloudFormation, or similar)
• Experience setting up CI/CD pipelines
• Understanding of service deployment, monitoring, and troubleshooting

Data Science/Analytics

• Experience with data analysis using Python (pandas, numpy)
• Understanding of data pipelines and ETL processes

AI/LLM Engineering

• Experience integrating LLM APIs (OpenAI, Anthropic, Gemini, or open-source equivalents) into production applications
• Understanding of core LLM concepts: context windows, token limits, temperature, system prompts, and model selection trade-offs
• Experience with prompt engineering techniques — few-shot prompting, chain-of-thought, structured output, and instruction tuning
• Practical knowledge of RAG (Retrieval-Augmented Generation) architectures, including chunking strategies, vector embeddings, and similarity search
• Familiarity with LLM orchestration frameworks such as LangChain, LlamaIndex, or similar
• Experience designing and building agentic systems — tool-calling agents, multi-step reasoning, and human-in-the-loop workflows
• Understanding of MCP (Model Context Protocol) or similar standards for connecting AI models to external tools and data sources
• Knowledge of LLM evaluation methods — measuring accuracy, hallucination, latency, and cost
• Awareness of responsible AI practices: bias, safety, output validation, and guardrails in production systems
• Experience managing LLM costs and optimising for latency vs. quality trade-offs in real deployments

Soft Skills

• Wearer of Many Hats: Comfortable switching contexts and working across different domains
• Self-Starter: Ability to work independently and take ownership of projects
• Problem Solver: Strong analytical and debugging skills
• Collaborative: Excellent communication skills and ability to work in a small team
• Adaptable: Comfortable with ambiguity and rapid iteration
• Mentoring: Able to mentor less-experienced Software Engineers.

Nice-to-Have Qualifications

• Experience with FastAPI or similar async Python web frameworks
• Experience with Neo4j or other graph databases
• Experience with graph algorithms and network analysis
• Experience with Helm and Kubernetes operators
• Background in data science, statistics, or scientific computing
• Experience with graph analytics or network analysis
• Experience with Apple and Google App Stores
• Experience in early-stage startups

What We Offer

• Impact: Direct influence on product direction and technical decisions
• Growth: Opportunity to work across the entire stack and learn new technologies
• Ownership: Take ownership of features from conception to deployment
• Flexibility: Hybrid, remote-friendly work environment
• Equity: Meaningful equity stake in the company
• Learning: Access to cutting-edge technologies and challenging problems

How to Apply

Please submit:

1. Your resume/CV
2. A brief cover letter explaining why you're interested in this role
3. Links to your GitHub profile or relevant code samples
4. Any relevant projects or work that demonstrates your experience

We're particularly interested in candidates who can demonstrate:

• Experience building scalable backend systems
• Ability to work across multiple domains (backend, DevOps, data)
• Examples of taking projects from idea to production
• Contributions to open source or personal projects

Note: Prolo is a startup with a small engineering team, which means you'll be expected to be versatile, proactive, and comfortable with ambiguity. If you're excited about building something from the ground up and working across the entire technology stack, we'd love to hear from you.