AI Engineer (Multi-Agent LLM Systems)

Makati, Metro Manila, Philippines

Sovrun

Sovrun is revolutionizing gaming through onchain ecosystems, autonomous worlds, and player-driven experiences. Empowering creators, communities, and players with tools to shape immersive, decentralized games and economies. Discover the future...

View all jobs at Sovrun

Apply now Apply later

We are seeking an experienced AI Engineer specializing in multi-agent LLM systems. This role requires a deep understanding of constructing, training, and deploying AI agents that can dynamically execute Python-based functions in response to specified needs. As part of our team, you’ll develop agents that can autonomously select and perform functions based on contextual requirements and work seamlessly within a robust AWS infrastructure.

Responsibilities:

  • Design, implement, and deploy AI agents that can autonomously learn to select and execute custom functions using Python.
  • Train agents to recognize contextual prompts and determine the necessary function to perform specific tasks, optimizing for accuracy and efficiency.
  • Develop frameworks for dynamic task assignment within multi-agent systems, enabling agents to coordinate and collaborate effectively on complex workflows.
  • Deploy and manage the multi-agent system within the AWS environment (e.g., Lambda, SageMaker, EC2), ensuring scalability and resilience.
  • Work closely with cross-functional teams to define function requirements and develop APIs or connectors for seamless task execution.
  • Implement strategies to improve model performance in function execution, covering error handling, retry mechanisms, and adaptability to changing requirements.
  • Document designs, workflows, and function-specific agent behaviors to support team collaboration and product transparency.

Requirements

  • Proven Experience: 1+ years working with LLMs, with a strong focus on developing function-driven multi-agent systems.
  • Experience in using LangChain/LangFlow/LangGraph is required.
  • Technical Skills: Expertise in Python and experience with custom function execution within LLM frameworks; skilled in prompt engineering, model fine-tuning, and dynamic function mapping. Experience in OpenAI Swarm and other relevant tech is a plus.
  • AWS Expertise: Demonstrated ability to deploy and manage models within AWS, using Lambda, SageMaker, EC2, and other essential AWS tools.
  • Web3 Knowledge: Familiarity with blockchain principles and web3 technologies is a plus.
  • Problem-Solving Skills: Experience developing autonomous, adaptable agents capable of selecting and performing tasks based on contextual cues.
  • Communication: Strong documentation skills for cross-functional alignment and clear communication of complex workflows.

Preferred Qualifications:

  • Experience with reinforcement learning or decision-making models to enhance autonomous task selection.
  • Familiarity with Docker and Kubernetes for robust, containerized deployments.
  • Previous experience in web3 or blockchain environments, including working with smart contracts or decentralized applications.

Benefits

  • HMO
  • Work From Home
  • Tokens
  • Leave Credits
  • Training & Development


Apply now Apply later

* Salary range is an estimate based on our AI, ML, Data Science Salary Index 💰

Job stats:  6  1  0

Tags: APIs AWS Blockchain Docker EC2 Engineering Kubernetes Lambda LangChain LLMs OpenAI Prompt engineering Python Reinforcement Learning SageMaker

Perks/benefits: Career development Transparency

Region: Asia/Pacific
Country: Philippines

More jobs like this