Backend Engineer (AI Stack) - Ladder

 

Role: Backend Engineer

Rank: Mid to ****Senior-level

Location: Hybrid (Ghana)

Commitment: Full Time

Salary: GHS 9,600 - 16,000

🚀 Ladder is an innovative tech startup that leverages AI to automate and simplify financial management. Our platform helps users manage their savings, investments, and expenses with support from their personalized AI financial assistant, LADY.

LADY is a multi-modal agent system specialized to analyze user’s financial data and provide them with step by step guidance to efficiently manage their money and achieve their financial goals. If this is your jam, and you’re passionate, forward-thinking, biased for execution and impact, we’d love to have you.

What you’ll do day-to-day

We are seeking a talented Backend Engineer to architect and optimize backend solutions, with a focus on data engineering, AI and large language model (LLM) implementations. As an LLM Backend Engineer at Ladder, you’ll be responsible for developing, scaling, and maintaining LLM-based applications and services. You will work closely with our AI, systems, and cross-functional product delivery teams to drive our mission forward by delivering AI-driven insights and tools that elevate our users' experience. You will be expected to:

1. Understand and analyze product requirements and communicate with the product and AI teams
2. Write clean, high-quality, high-performance, and scalable backend code for LLM integration
3. Design, develop, and maintain APIs that support AI-driven applications and interact with large language models
4. Optimize database interactions, manage data flows, and implement efficient data caching techniques for LLM applications
5. Coordinate with cross-functional teams to ensure alignment with business objectives and compliance standards
6. Participate in code reviews, technical planning, and LLM model fine-tuning sessions
7. Implement automated testing platforms, monitor AI service performance, and support deployment of new AI-driven features
8. Stay updated on advancements in LLM technology and bring best practices to our team

Work Hours

This role is expected to put in a total of 40 hours of quality work weekly between 9:30 AM to 5:30 PM GMT.

Main Stack

LLM Frameworks: OpenAI, LangChain

Programming Language: Python,

LLMOps: fastAPI, Guardrails-ai + Semantic router + Redisvl(SemanticCache/llmcache)

Backend Framework: FastAPI, Django (DRF)

Data store: PostgreSQL, Redis for caching

CI/CD: GitHub Actions, Docker

Infrastructure: AWS, Kubernetes

Requirements

1. Proven experience in backend development, ideally in data engineering, AI/ML or large language model applications
2. Strong proficiency in Python, with demonstrated expertise in frameworks like FastAPI and Django
3. Proficiency in designing RESTful APIs and managing high-traffic AI model requests
4. Knowledge of database optimization, query handling, and data flow for LLM data pipelines
5. Familiarity with Docker, cloud infrastructure (AWS preferred), and CI/CD tools
6. Ability to communicate effectively across teams, bringing clarity to technical and product discussions
7. A sense of ownership and an innovative mindset with an ability to identify areas for AI-driven improvements

Nice to haves:

1. Interest in experimenting with emerging LLMs and AI techniques to push the boundaries of what's possible
2. Experience with LLM frameworks (e.g., Hugging Face, OpenAI API, LangChain) and integrating LLMs into backend systems

How to apply

Interested individuals can apply now. Please send a copy of your CV to careers@myladder.africa with a link to your GitHub profile. Only shortlisted candidates will be contacted