17
applicants

Software Engineer

Homey    Colombo • Full-time

Description

Designs, develops, and deploys advanced AI-powered applications leveraging Large Language Models (LLMs), prompt engineering, and modern orchestration frameworks. This role aligns with industry titles such as Senior AI Engineer, Senior Machine Learning Engineer (LLM-focused), and Generative AI Engineer.

Synopsis

Leads the design and development of scalable AI-driven systems, focusing on LLM integrations, prompt optimization, and agent-based workflows, while ensuring high performance, reliability, and production readiness.

Responsibilities

  • Design, develop, and maintain AI-powered applications using LLMs, prompt engineering, and orchestration frameworks (e.g., LangGraph, LangChain).
  • Build and optimize prompt strategies for accuracy, performance, and cost efficiency across different LLM providers.
  • Architect and implement agent-based workflows and multi-step reasoning systems using modern AI frameworks.
  • Integrate LLM solutions into scalable backend systems and APIs.
  • Evaluate, fine-tune, and monitor AI models for performance, bias, and reliability.
  • Ensure security, compliance, and responsible AI practices in all implementations.
  • Collaborate with cross-functional teams including Product, DevOps, and Data teams to deliver AI-driven features.
  • Establish best practices for AI engineering, prompt versioning, and experimentation frameworks.
  • Optimize system performance, latency, and cost when working with AI services.
  • Contribute to CI/CD pipelines for AI applications and ensure smooth deployment cycles.
  • Stay up to date with emerging trends in Generative AI, LLMs, and AI tooling.

Requirements

  • Bachelor's degree in computer science, Software Engineering, or related field.
  • 4–7+ years of experience in software engineering, with hands-on experience in AI/ML or LLM-based systems.
  • Strong experience with prompt engineering and LLM APIs.
  • Hands-on experience with frameworks such as LangGraph, LangChain, or equivalent orchestration tools.
  • Proficiency in at least one programming language such as Python, JavaScript/TypeScript, or Java.
  • Strong understanding of REST APIs, microservices architecture, and cloud environments (preferably AWS).
  • Experience with AI evaluation techniques, prompt testing, and model performance tuning.
  • Familiarity with CI/CD, DevOps practices, and containerization (Docker/Kubernetes).
  • Solid understanding of software engineering best practices, including testing, security, and scalability.
  • Strong problem-solving skills and ability to work independently in a fast-paced environment.

Nice to Have

  • Experience with fine-tuning LLMs or open-source models (e.g., LLaMA, Mistral).
  • Knowledge of multi-agent systems and AI workflow orchestration.
  • Exposure to data pipelines, NLP techniques, or deep learning frameworks (PyTorch/TensorFlow).
  • Experience in cost optimization strategies for AI systems.
  • Contributions to open-source AI projects or research publications.