Senior AI/LLM Engineer (Python) - Remote

Kake; Toronto; À distance; CAD 171 000 - 257 000; Plein temps

Avantages offerts par ce poste

Competitive USD pay

Fully remote work

Better Me Fund

Compassion is Badass

Résumé du poste

Kake is a remote-first, people-first global community of senior engineers. We design and scale LLM-powered applications for Fortune 500s and growing companies, with a community of 45,000+ engineers across 55+ countries.

Senior AI/LLM Engineers will own end-to-end features, integrate with multiple LLM providers, and build robust RAG pipelines in a fast-paced, fully remote setting. Strong Python and backend experience are essential for success.

Qualifications

• Fluent English communication and collaborative work in remote teams.
• Experience designing and delivering LLM-powered features at scale.
• Strong Python backend development experience and API design.
• Comfortable working in a fast-paced, remote environment and across time zones.
• Familiarity with AI safety, evaluation, and testing practices.

Responsabilités

• Design, build, and deploy LLM-powered features and applications using Python.
• Develop and maintain backend services and APIs (e.g., FastAPI) exposing AI capabilities.
• Build and optimize RAG pipelines, embeddings, and vector search strategies.
• Design, test, and iterate prompts, agents, and orchestration using LangChain / LlamaIndex.
• Integrate with LLM providers (OpenAI, Anthropic) and manage cost, latency, and quality.
• Ensure production AI systems are tested for accuracy, safety, and reliability.

Connaissances

Python

English communication

Remote work

Backend development

AI systems design

Outils

FastAPI

LangChain

LlamaIndex

OpenAI API

Anthropic API

Pinecone

Weaviate

pgvector

Docker

PostgreSQL

Redis

Description du poste

Kake is a remote-first company and a people-first global community of senior engineers. Kake engineers are behind some of the world’s most innovative products (Brands you’ve heard!), from Fortune 500 to fast-growing companies. We believe it’s not where your table is, but what you bring to the table that matters. Our community spans 45,000+ engineers across 55+ countries; join a culture where great people stay, grow, and thrive (and love eating kake!).

Senior AI/LLM Engineers with strong Python experience, skilled in designing, building, and productionizing LLM-powered applications and AI systems at scale. It's a great fit for people who enjoy working at the intersection of software engineering and applied AI, and who take ownership from prototyping through production deployment.

What you’ll build and own

• Design, build, and deploy LLM-powered features and applications using Python.
• Develop and maintain backend services and APIs (e.g., FastAPI) that expose AI/LLM capabilities to other systems.
• Build and optimize RAG pipelines, including embeddings, vector search, and retrieval strategies.
• Design, test, and iterate on prompts, agents, and orchestration flows using frameworks such as LangChain, LlamaIndex, or similar.
• Integrate with LLM providers and APIs (e.g., OpenAI, Anthropic, open-source models) and manage tradeoffs around cost, latency, and quality.
• Evaluate model outputs systematically, building tooling and metrics to test accuracy, safety, and regression across iterations.
• Work with containerized environments and data infrastructure (e.g., PostgreSQL, Redis, vector databases) to support reliable AI systems in production.
• Collaborate with cross-functional stakeholders to translate ambiguous product needs into technically sound AI solutions.

Core Requirements

• Strong proficiency in Python and experience with FastAPI or similar backend frameworks.
• Experience working with LLM APIs (e.g., OpenAI, Anthropic, or similar) and frameworks such as LangChain or LlamaIndex.
• Experience with RAG architectures, embeddings, and vector databases (e.g., Pinecone, Weaviate, pgvector, or similar).
• Hands-on experience with Docker and containerized development environments.
• Experience working with PostgreSQL, Redis, or similar data stores.
• Strong experience writing functional and integration tests, including evaluation frameworks for AI/LLM output quality.
• Excellent written and verbal communication skills in English.
• Ability to work independently in a remote, fast-paced environment.

Nice-to-Have

• Experience fine-tuning or evaluating open-source LLMs.
• Familiarity with prompt engineering best practices and agentic workflows.
• Experience with distributed systems, streaming (e.g., Kafka), or large-scale applications.
• Background in machine learning fundamentals (e.g., scikit-learn, PyTorch, or TensorFlow).
• Comfortable working flexible hours to overlap with distributed teams across different time zones.

Why Join Kake?

The icing on the Kake:

• Competitive Pay in USD: Work globally, get paid globally.
• Fully Remote: Simply put, we trust you.
• Better Me Fund: We invest in your personal growth and passions.
• Compassion is Badass: Join a community that invests in social good.

Ready for your piece of the Kake?

Quick note: Due to the high volume of applications, only shortlisted candidates will be contacted.