AI Engineer

About the Company and Role

Pokee is developing an agentic workflow platform designed to simplify AI integration and facilitate dependable, reproducible workflows. They seek a motivated AI Engineer to collaborate across machine learning, product, and engineering teams in delivering AI solutions ready for production deployment.

Key Responsibilities

• Develop production-level AI systems bridging machine learning, product development, and software engineering.
• Implement AI-driven features for enhanced user experience and business growth.
• Innovate and push the limits of generative AI models and agent architectures.
• Design scalable AI capabilities focused on discovery, in-depth research, and monetization.
• Create evaluation platforms that assess answer quality, model effectiveness, and product impact.
• Utilize state-of-the-art approaches for personalization, query understanding, and information retrieval.
• Construct AI agent systems, including tool creation, prompt engineering, and optimizing architecture.
• Enhance system performance, dependability, and cost-effectiveness through strategic design choices.

Qualifications and Experience

• Possess a BS, MS, or PhD degree in Computer Science or a closely related discipline.
• Demonstrate over three years of experience in building and delivering AI or software products in production settings.
• Experience working with agentic applications, tool invocation methods, and model serving architectures.
• Strong backend development and systems design skills, balancing cost, latency, and quality tradeoffs.
• Advanced programming proficiency in Python, adhering to production-level code quality standards.
• Self-motivated with high autonomy and a drive to produce impactful work expediently.

Desired Expertise

• Advanced knowledge in PyTorch and/or TensorFlow frameworks.
• In-depth experience with large language models (LLMs).
• Expertise in information retrieval systems and natural language processing (NLP).
• Experience with relevance ranking systems and optimization.
• Proficiency in reinforcement learning with human feedback (RLHF), reward modeling, supervised fine-tuning (SFT), and instruction tuning.
• Skills in optimizing model inference and serving AI models efficiently.