Senior Software Developer, AI Agents

The Role: Senior Software Developer, AI Agents

We’re looking for an experienced software developer to build and scale the  AI agents behind Knak’s platform. In this role you'll develop the agent harness itself: the orchestration, tool calling, context management, and guardrails that let agents analyze data, generate complex marketing assets, and deliver real value to our customers. You'll also ensure we know they work, by building the evaluation suites that measure agent quality and catch regressions before they reach customers.

This is a hands-on role for someone who wants to be deep in agent internals every day. You'll also contribute to architecture decisions, mentor teammates, and collaborate across engineering and product to shape the future of marketing automation.

What You’ll Be Doing

• Build the agent harness: Design and implement the core agent runtime in Python: orchestration loops, tool definitions and execution, memory and context management, structured outputs, and failure handling.
  
  
• Own agent evaluations: Build and maintain eval datasets, automated evaluators, and LLM-as-judge pipelines (LangSmith) so every prompt, model, or harness change is measured, not guessed at.
  
  
• Iterate on agent quality: Diagnose agent failures from traces, tune prompts and tool designs, and run model comparisons and benchmarks to drive measurable improvements.
  
  
• Create AI microservices: Build Python and Node.js services for agent hosting and LLM interaction.
  
  
• Build reliable APIs: Develop and maintain the Laravel (PHP) APIs that integrate agents into the Knak platform, ensuring testability, observability, and performance.
  
  
• Deploy to the cloud: Use AWS services (Lambda, Bedrock, CDN delivery) to build secure, scalable infrastructure for agents.
  
  
• Optimize databases: Tune MySQL queries and indexing to improve speed and reduce latency.
  
  
• Elevate code quality: Lead and participate in code reviews, maintaining high standards across the team.
  
  
• Collaborate cross-functionally: Work with product, design, QA, and DevOps to align solutions with business needs.
  
  
• Mentor engineers: Share knowledge on agent development and evaluation practices, and set a high bar for technical excellence.

What You Should Bring

• 6+ years of software development experience
  
  
• Hands-on experience building LLM-powered agents in production, including tool calling, orchestration, context management, and prompt engineering
  
  
• Experience designing and running evaluations for LLM systems, including dataset curation, automated evaluators, LLM-as-judge, and regression tracking
  
  
• Strong proficiency in Python, Node.js, and MySQL
  
  
• Expertise in RESTful APIs, TDD, CI/CD (GitHub Actions)
  
  
• Experience with SaaS architecture, microservices, and AWS
  
  
• Knowledge of observability, performance tuning, and scalability
  
  
• Familiarity with Docker/Kubernetes
  
  
• Excellent problem-solving skills and a collaborative mindset
  
  

Nice to Have

• Interest in, or experience with, full-stack web development spanning frontend (e.g. Vue), backend (e.g. PHP Laravel), and agent engineering, with a willingness to work across all three as the product needs
  
  
• Experience in AI-powered product development
  
  
• Background with LLMs, LangGraph, or AI agent frameworks
  
  
• Prior experience in a fast-growing SaaS company

Base Salary: The anticipated base salary range for this position is $1350,000 - 170,000k/year. Final compensation will be determined based on factors including relevant experience, skills, qualifications, and internal equity. This range reflects base salary only and does not include other forms of compensation that may be available as part of the total rewards package.