AI Engineer

About Knotch We're a growth-stage technology company helping brands optimize content performance and apply AI to modern marketing. Our culture is fast-paced, entrepreneurial, and highly adaptable—we move quickly, test ideas, and evolve with our customers. Through the Knotch platform, brands can measure the impact of their content, identify what drives results, and continuously improve performance across channels. By combining performance data, strategic insights, and AI-driven capabilities, we help marketing teams make smarter decisions and get more impact from every piece of content they produce. About the Role Most companies building AI agents are starting from scratch. Knotch isn't. We've spent years accumulating one of the richest proprietary datasets in B2B content intelligence — deep signals on how content performs, what drives engagement, and what separates great content from noise. That data is our unfair advantage, and we're now ready to unleash it. We're at the beginning of an exponential shift — moving from a platform that surfaces insights to one that autonomously acts on them through Gen AI and Agentic AI. As a Senior AI Engineer, you'll have access to a unique data foundation and a leadership team fully committed to making AI central to everything Knotch does. This is a rare chance to build consequential AI — not demos, not experiments, but production-grade agents that enterprise clients depend on. This isn't an AI layer bolted onto an existing product. This is a ground-up reimagining of what content intelligence can be in the age of large language models and agentic AI. You'll shape not just how we build, but what we build and why. If you want to own the architecture, influence the roadmap, and watch your work directly move the needle for enterprise clients — this is that role. If you've made it this far, please kindly input this code with your application: AI-ENG-2026. Responsibilities Develop and deploy AI agents that automate complex workflows across the Knotch platform. Build the internal tools and infrastructure that power, monitor, and maintain these agents in production. Design and implement backend and frontend services, APIs, and data pipelines, integrating AI functionality into user-facing features. Contribute to system architecture and core platform design alongside the broader engineering team. Collaborate closely with Product, Data Engineering, Backend, and Frontend teams to align AI capabilities with product direction and ensure seamless integration across the stack. Design and maintain a suite of evaluations and benchmarks to measure agent accuracy, reliability, and cost-effectiveness. Optimize inference pipelines and backend systems for speed, scalability, and cost. Own the AI safety and governance layer — guardrails, audit logging, fallback logic, and access controls that ensure our agents operate reliably and responsibly. Qualifications You have at least 3+ years of software engineering experience building and shipping LLM-powered applications, within within SaaS startup environments (marketing or digital analytics experience is considered an asset) . Must Haves Prior startup, growth-stage, or SaaS platform experience working in fast-paced, agile environments. Hands-on experience building production AI agents using LLM orchestration frameworks — LangGraph, LangChain, or similar. Deep familiarity with agentic patterns — tool/function calling, multi-agent orchestration, memory management, and MCP. Strong Python proficiency and backend API development experience. Data Engineering and/or analytics background, including building pipelines, transformations, and querying data warehouses like Snowflake. Solid grounding in NLP concepts — tokenization, embeddings, semantic similarity, and how language models process and generate text. Experience building RAG pipelines and integrating LLMs against structured data sources. Prompt engineering fluency — systematic design, structured outputs, and schema definitions. An evaluation and observability mindset — you think about how to measure and monitor agent behavior, not just ship it. Nice-to-Haves (not mandatory) Experience with vector databases (Pinecone, pgvector, Weaviate) or data warehouses like Snowflake. Familiarity with AI guardrail frameworks — Guardrails AI, NeMo Guardrails, or LlamaGuard. Exposure to fine-tuning techniques — LoRA, PEFT, or instruction tuning. Prior experience in a founding or first AI engineer role. How to be Successful Have hands-on experience building and shipping LLM-powered applications: you’ve moved beyond prototypes and understand what it takes to run reliable AI systems in production. Strong intuition for agentic design patterns: you can effectively leverage tool calling, multi-agent orchestration, memory, and MCP to solve real-world problems. Fluency in modern AI frameworks and backend systems: you’re comfortable working with tools like LangGraph or LangChain, and building robust Python-based APIs. Deep understanding of NLP and LLM behavior: you grasp concepts like embeddings, tokenization, and semantic similarity, and use that knowledge to build better systems. Thoughtful prompt and system design: you approach prompt engineering methodically, with an emphasis on structured outputs and reliability. Evaluation and observability focus: you don’t just ship agents; you think critically about how to measure, monitor, and improve their performance over time. Ownership and initiative: you take responsibility for your work, influence technical direction, and proactively identify opportunities to improve systems. Adaptability and curiosity: you stay on top of a rapidly evolving AI landscape and are eager to experiment, learn, and apply new techniques. Why Join Knotch We offer a unique opportunity to work with a powerful data moat built on years of proprietary B2B content intelligence, fuelling AI capabilities that competitors simply can’t replicate. Our modern AI stack includes tools like LangGraph, Claude, and Snowflake, supported by a team already executing on an AI-native architecture. You’ll have real ownership, with direct influence over system design, product direction, and roadmap decisions. The work is deeply consequential: the agents you build will be deployed in production for enterprise clients from day one, not confined to a sandbox. Most importantly, you’ll be backed by committed leadership — at Knotch, AI isn’t a side initiative; it’s the company’s next chapter. The expected salary range for this opportunity is $140,000–$220,000 USD depending on experience. Our Benefits and Perks Knotch is a fully remote company. Candidates may work from anywhere in the U.S., EST time zone preferred . Some of our other great benefits include: Comprehensive medical, dental, and vision insurance eligibility 401(k) plan Unlimited PTO 10+ company-paid holidays A daily company-wide break, and more! Equal Opportunity Employer Knotch is a US-based equal opportunity employer. We strive to provide equal opportunities in all of our processes, including our hiring and employee experience. We pride ourselves on our three values: transparency, relentlessness, and inclusiveness. We commit to daily work towards leading with empathy, reducing bias through periodic training, and engaging with and uplifting communities of marginalized groups. We condemn all forms of racism and discrimination on the basis of race, religion, ethnicity, nationality, gender identity, sexual orientation, age, marital status, pregnancy or parenthood status, veteran status, disability status, or any other identifier. We encourage all employees, clients, investors, candidates, vendors, and friends of Knotch to deliver honest feedback directly or anonymously so that we may always seek to improve as an organization dedicated to diversity, equity, inclusion, and belonging.