Role Overview
We are seeking a talented AI/ML Engineer to design, develop, and optimize next-generation AI-powered applications and intelligent agent systems. Working with cutting-edge large language models, modern AI frameworks, and scalable backend technologies, you will build reliable, production-ready solutions. You will own AI agent development, prompt engineering, retrieval-augmented generation, and intelligent workflow orchestration, collaborating with engineering and product teams to turn emerging AI capabilities into practical, high-value features. This is a hands-on role for an engineer who enjoys experimentation and solving complex technical challenges in a fast-paced, remote-first environment.
Responsibilities
- Lead development and continuous improvement of AI-powered applications, combining advanced ML with robust software engineering for scalable production systems.
- Design, develop, and enhance AI agent capabilities using modern LLMs.
- Build scalable backend services and RESTful APIs with Python and FastAPI.
- Develop and optimize prompt workflows, RAG pipelines, and AI agent orchestration.
- Integrate AI APIs and third-party services into intelligent, scalable applications.
- Experiment with emerging AI models and tools to identify innovation opportunities.
- Evaluate model performance, reliability, accuracy, and quality, implementing improvements.
- Collaborate with engineering and product teams to deploy AI-powered features.
- Deploy, monitor, maintain, and optimize AI systems in production.
- Continuously test and refine to improve efficiency, scalability, and reliability.
- Stay current on generative AI, machine learning, and agent-based architectures.
Requirements
- Strong professional software engineering experience with Python.
- Hands-on experience developing applications powered by large language models (LLMs).
- Experience integrating AI APIs and building intelligent, AI-driven applications.
- Familiarity with AI agent frameworks such as LangChain, LangGraph, LlamaIndex, or comparable technologies.
- Experience designing and developing backend APIs using FastAPI or similar frameworks.
- Knowledge of cloud infrastructure and deployment environments, preferably AWS, GCP, or Azure.
- Strong understanding of generative AI concepts, prompt engineering, and AI application development.
- Excellent analytical, troubleshooting, and problem-solving skills.
- Strong communication and collaboration abilities across engineering and product teams.
- Ability to work independently, manage priorities, and adapt to a fast-paced remote environment.
Additional Qualifications
- Experience deploying production-ready AI agents or generative AI products.
- Knowledge of retrieval-augmented generation (RAG), tool calling, prompt optimization, and model evaluation techniques.
- Experience designing multi-step AI workflows and sophisticated agent orchestration systems.
- Contributions to open-source AI projects or independent AI applications.
- Familiarity with monitoring, evaluating, and optimizing AI systems in production.
- Previous experience within AI-first technology organizations.