Software Engineer - AI

About Kredivo Group

Kredivo Group is a rapidly expanding fintech firm based in Singapore committed to enhancing financial inclusion through technological innovation. Serving multiple Southeast Asian markets and beyond, the company develops and scales responsible credit solutions and financial products targeted at underserved individuals and small enterprises.

Role Overview

You will join the AI Transformation team tasked with crafting an internal AI platform that empowers employees to utilize AI effectively and expedite software development with increased confidence. Key projects involve an agentic AI system that facilitates workflow automation across internal tools, AI-facilitated software development lifecycle (SDLC) automation aimed at improving software design, testing, and deployment processes, plus a centralized knowledge base ensuring reliable access to organizational context.

As a Software Engineer focused on AI, you will be hands-on, owning significant segments of the AI platform from conception through deployment and upkeep. Your initial assignments will align with team priorities and your relevant experience.

Key Responsibilities

• Develop scalable production AI applications and services; design backend services, RESTful APIs, integrations, and large language model (LLM)-enabled agent workflows that resolve challenges faced by internal users.
• Take full ownership of project delivery phases: gather and clarify requirements, make informed design decisions, author clean and testable code, perform safe deployments, manage and troubleshoot live systems, and iteratively enhance delivered solutions.
• Utilize agentic AI development tools to rapidly prototype and advance software capabilities while maintaining responsibility for security, design integrity, and production quality.
• Leverage testing methodologies, observability tools, user feedback, and LLM evaluation frameworks to detect issues and elevate application performance.
• Collaborate with internal teams to translate effective solutions into reusable platform components with comprehensive documentation for broader adoption.
• Work closely with engineering, product management, security, data science, and business units to foster AI platform growth with attention to data security, privacy, and structured change management.

Mandatory Qualifications and Experience

• Minimum of 3 years professional experience developing backend systems with Python, involving design, deployment, and operational management of backend services or APIs in production environments.
• At least 2 years hands-on experience with relational databases like PostgreSQL or MySQL, including schema design, crafting SQL queries, optimizing indexing, and troubleshooting query performance issues.
• Over 2 years practical experience deploying, operating, and monitoring backend solutions on cloud platforms such as AWS or GCP, utilizing containerization technologies like Docker or Kubernetes alongside CI/CD pipelines.
• Experience building applications powered by LLMs involving agents that utilize tools or execute multi-step workflows, with familiarity in techniques such as retrieval-augmented generation (RAG), prompt management, multi-provider integration, response streaming, or agent frameworks like LangChain, LangGraph, or Strands.
• Hands-on use of AI software development agents (e.g., Claude Code, Codex) for accelerating prototyping, code writing, testing, debugging, and code reviewing tasks.
• Strong analytical and problem-solving aptitude with capability to decompose ambiguous challenges, evaluate trade-offs, and produce maintainable and effective code. Excellent communicator able to work collaboratively within interdisciplinary teams, providing and receiving constructive feedback.

Desired Additional Expertise

• Educational background in Computer Science, Software Engineering, or equivalent hands-on experience is advantageous.
• Experience scaling LLM platforms serving over 1,000 active users, with skills in managing latency, concurrency, reliability, and cost-efficiency as system usage expands.
• Up-to-date knowledge of avant-garde LLM capabilities and tooling, including multi-channel protocols (MCP/A2A), agent state/memory handling, regression testing, safe code executions, model routing, low-latency UI streaming, and model fine-tuning.
• Expertise in enterprise knowledge search and retrieval systems integrating AI applications with internal data repositories, ensuring relevance, source tracking, and access control.
• Familiarity with adapting LLMs for production deployment including supervised fine-tuning, parameter-efficient tuning methods like LoRA, reinforcement learning techniques (DPO, RLHF, GRPO), distillation, continued pretraining, model quantization, and optimized inference engines such as vLLM.
• Experience working in a startup or early-stage product environment, comfortable with fast-paced development cycles, ambiguous requirements, rapid iteration, and balancing speed with high-quality delivery.