Role Overview
We are seeking a highly skilled AI Agent Engineer to design, build, and deploy advanced AI agents that leverage cutting-edge large language models (LLMs) to solve complex real-world problems. These AI agents are intricate software systems that simulate human-like reasoning, decision-making, and creativity to tackle business challenges autonomously.
In this pivotal role, you will drive the development of intelligent agents from concept through production, integrating them into scalable applications and ensuring they operate reliably at scale. You'll be instrumental in building the core intelligence of our products, working across the entire AI/ML lifecycle in a collaborative, high-trust environment.
This role is fully remote and open to candidates globally, allowing you to contribute from anywhere while collaborating with a diverse, distributed team.
Key Responsibilities
Agent Development & Architecture
- Design, develop, and maintain intelligent AI agent systems that exhibit autonomous decision-making and action-taking capabilities
- Prototype and implement LLM-based agent solutions from concept to production, ensuring meaningful real-world outcomes
- Orchestrate multi-step workflows and design multi-agent architectures using frameworks like LangChain, AutoGPT, or Semantic Kernel
Integration & Infrastructure
- Integrate external APIs and tools to enable agents to interact with various systems, orchestrating end-to-end task automation beyond simple question-answering
- Build and optimize software infrastructure and data pipelines for AI/ML models, ensuring scalability and efficiency
- Implement and fine-tune Large Language Models (LLMs) and other generative AI techniques for agentic applications
Knowledge Management & Context
- Manage contextual knowledge bases by implementing and maintaining vector databases or retrieval systems (Pinecone, FAISS, etc.)
- Develop techniques for grounding generative models with external knowledge sources using RAG, Knowledge Graphs, and semantic retrieval
Performance & Production
- Deploy AI agent systems into high-throughput, low-latency production environments
- Take ownership of performance, scalability, and reliability through rigorous testing, monitoring, and optimization
- Monitor and enhance system performance, identifying bottlenecks and implementing updates
Research & Innovation
- Conduct continuous improvement and R&D by experimenting with the latest AI models, tools, and frameworks
- Stay up-to-date with emerging developments in the AI/ML space and agentic techniques
- Ensure ethical development and deployment of AI agents, addressing potential biases and security implications
Collaboration
- Work closely with software engineers, product managers, design teams, and researchers to integrate AI agents into products and workflows
- Collaborate cross-functionally to deliver robust AI solutions with seamless user experiences
- Contribute to a culture of rapid innovation and ethical AI development
Required Qualifications
Education & Experience
- Bachelor’s or master’s degree in computer science, Artificial Intelligence, Machine Learning, or related technical field (or equivalent practical experience)
- 5+ years of experience in software development
- 1-2+ years of experience working with Large Language Models (LLMs) in production environments
- 1-2+ years of experience building and deploying AI agent systems or similar autonomous systems
- 1-2+ years of experience developing and deploying machine learning models in production
Technical Skills
- Programming: Strong proficiency in Python and familiarity with software engineering best practices
- AI/ML Libraries: Experience with TensorFlow, PyTorch, and other relevant AI/ML frameworks
- LLM Expertise: Significant expertise in prompt engineering, fine-tuning, and working with AI/LLM APIs (OpenAI, Anthropic Claude, etc.)
- Agent Frameworks: Proficiency with AI agent development frameworks (LangChain, LlamaIndex, AutoGPT, Semantic Kernel)
- Vector Databases: Familiarity with vector databases and retrieval-augmented generation techniques
- Software Architecture: Solid understanding of software design patterns and ability to write clean, maintainable, scalable code
- MLOps: Familiarity with MLOps principles and tools for model deployment and monitoring
Soft Skills
- Strong problem-solving, analytical, and critical thinking skills
- Excellent communication and collaboration abilities with a proactive approach to teamwork
- Demonstrated understanding of ethical AI development, including bias identification and mitigation
- Continuous learning mindset and adaptability to a fast-paced, evolving startup environment
Preferred Qualifications
Advanced Technical Experience
- Experience deploying AI solutions on cloud infrastructure (AWS, GCP, Azure)
- Familiarity with containerization and MLOps tools (Docker, Kubernetes)
- Knowledge of reinforcement learning or advanced multi-agent system design
- Experience with techniques for fine-tuning or aligning LLMs
- Experience deploying AI models at scale in high-throughput, low-latency environments
Portfolio & Education
- Portfolio of AI projects or notable open-source contributions (active GitHub projects highly valued)
- Master's or Ph.D. in Machine Learning, Computer Science, or related field
What We Offer
Compensation & Benefits
- Competitive salary and significant equity compensation, aligning your success with ours
- Comprehensive health, dental, and vision insurance
- Generous parental leave and flexible paid time off
- Dedicated budget for continuous learning, including courses and conference passes
Work Environment
- Opportunity to work on cutting-edge AI agent technology and solve impactful, novel problems
- A passionate, diverse, high-trust, and collaborative team culture
- Flexible work arrangements with full remote options available
- Fast-paced, innovative environment at the forefront of AI technology
Growth & Impact
- Work at the intersection of cutting-edge AI research and practical business applications
- Contribute to defining the future of autonomous AI systems
- Opportunity to drive significant operational efficiency and create novel value through AI innovation
