Senior AI/LLM Engineer (Python) - Remote

About Kake

Kake is a globally distributed, remote-first company committed to building a community of senior engineers. Our engineers contribute to innovative products for Fortune 500 companies as well as fast-growing startups. With a community of over 45,000 engineers across more than 55 countries, we foster a culture of growth, collaboration, and longevity.

Role Overview

We are seeking Senior AI/LLM Engineers who have strong experience in Python to design, develop, and deploy large language model-powered applications and AI systems at scale. Candidates will enjoy working at the intersection of applied AI and software engineering, taking end-to-end ownership from prototyping through production deployment.

Key Responsibilities

• Architect, develop, and deploy LLM-driven features and applications using Python.
• Create and maintain backend services and APIs (e.g., FastAPI) to expose AI and LLM functionalities to various systems.
• Build and optimize Retrieval-Augmented Generation (RAG) pipelines involving embeddings, vector search, and retrieval methods.
• Design, test, and refine prompts, agents, and orchestration workflows leveraging frameworks such as LangChain and LlamaIndex.
• Integrate with major LLM providers and APIs including OpenAI, Anthropic, and open-source alternatives, balancing factors like cost, latency, and quality.
• Implement evaluation tools and metrics to systematically assess model outputs for accuracy, safety, and regression during iterative improvements.
• Work with containerized environments and manage data infrastructure (PostgreSQL, Redis, vector databases) to ensure scalable AI systems in production.
• Collaborate cross-functionally to translate complex, ambiguous product requirements into technically robust AI-powered solutions.

Required Qualifications

• Proficient in Python programming with hands-on experience using FastAPI or comparable backend frameworks.
• Practical experience with LLM APIs (OpenAI, Anthropic, or equivalent) and frameworks such as LangChain or LlamaIndex.
• Familiarity with RAG architectures, embeddings, and vector database technologies like Pinecone, Weaviate, pgvector, or similar.
• Experience with Docker and containerized development workflows.
• Knowledge of PostgreSQL, Redis, or related database systems.
• Skilled in writing functional and integration tests including frameworks to evaluate AI/LLM outputs quality.
• Excellent communication skills in English, both written and verbal.
• Ability to work autonomously within a fast-moving, remote work setting.

Preferred Qualifications

• Experience with fine-tuning or assessing open-source large language models.
• Awareness of prompt engineering best practices and agent-oriented workflows.
• Experience with distributed systems, data streaming platforms such as Kafka, or large-scale software applications.
• Background knowledge in machine learning fundamentals involving libraries like scikit-learn, PyTorch, or TensorFlow.
• Flexibility to work hours overlapping US time zones approximately 5-6 hours daily PST.

Additional Information

• This role requires overlapping working hours with US-based teams between 5 to 6 hours daily PST.

Why Choose Kake?

• Competitive compensation paid in USD regardless of your global location.
• Fully remote work environment based on trust and autonomy.
• Access to the "Better Me Fund" supporting personal growth and passions.
• A community culture that values compassion and social good initiatives.