Generative AI Engineer
Knitit.ai
Company Overview: Knit.ai is an early-stage venture funded tech company with an innovative solution that empowers IT and security teams. We are building a data and AI driven application that assists IT and Security teams in vendor operations, performance management and strategic research. We are a team that moves fast but makes high-quality decisions. We value self-starters who can learn quickly, make mistakes but learn from them, and are accountable and hold others accountable to high standards.
Job Purpose: As an AI Engineer, you will play a crucial role in developing and implementing AI capabilities that enhance our core product offering. You will be responsible for evaluating, integrating, and orchestrating foundation models to solve complex problems for IT and security teams through well-designed code and thoughtful architecture.
Key Responsibilities:
Design and implement AI-powered features using modern LLMs and foundation models through APIs and open-source tools
Create robust prompting strategies and orchestration layers to ensure reliable, high-quality AI outputs
Develop and maintain retrieval-augmented generation (RAG) systems to enhance model performance with domain-specific knowledge
Build evaluation frameworks to measure model performance and ensure quality for production use
Optimize AI systems for reliability, response time, and cost efficiency
Collaborate with back-end developers to integrate AI capabilities with our core infrastructure
Research, test, and implement new AI techniques as they emerge to maintain competitive advantage
Design and implement data pipelines for training, fine-tuning, and evaluating models
Document AI systems and create internal knowledge resources for the broader engineering team
Stay updated with industry trends and emerging AI technologies
Skills and Qualifications:
Bachelor's degree in Computer Science, Engineering, or a related field
Minimum of 3 years of experience in software development, with at least 1 year focused on AI applications
Proficiency in Python and relevant AI/ML frameworks such as LangChain, LlamaIndex, or similar orchestration tools
Experience with vector databases and embedding models (e.g., Pinecone, Weaviate, ChromaDB)
Familiarity with cloud-based AI services from providers such as OpenAI, Anthropic, or Google
Strong understanding of software engineering principles and best practices
Experience with production AI systems and the challenges of deploying them at scale
Knowledge of prompt engineering techniques and LLM evaluation methodologies
Strong problem-solving skills, attention to detail, and ability to think critically
Excellent communication skills and the ability to explain complex AI concepts clearly
You don't just know what the right thing is to do, you know why it's the right thing and can articulate it
Reporting Structure: You will be reporting directly to the Chief Technology Officer (CTO) & Cofounder
Location: This position is based in Palo Alto, CA. We believe the power of collaboration and creativity is critical for an early stage startup and is best captured in-person, hence the expectation is for in-office work 5 days a week.
Employment Type: This is a full-time position offering a competitive salary, early stage startup equity, and benefits package, commensurate with your experience and skills.