Senior Full-stack LLM Engineer — The Suite (via Remotesome)

About The Suite

We are a team of 80+ of the world’s greatest community builders and technologists.

We build high-quality and highly-curated professional communities. We run three of these communities today, including our flagship The L Suite, which is a private, invite-only community for General Counsels / Chief Legal Officers and their teams at high-growth tech companies and venture funds. We also run The F Suite (for CFOs) and The E Suite (for CEOs), with more in the pipeline.

We currently have 5,000+ paid members across our communities, representing C-Suite executives and their deputies from most of today’s leading tech companies (e.g., OpenAI, Anthropic, Airbnb, Slack, Coinbase, Uber, Notion, Bolt, Figma, Airtable, Dropbox, Bilt, Datadog, etc.) and venture funds (e.g., a16z, Softbank, Tiger, Accel, Thrive, Battery Ventures, FirstMark, Kleiner Perkins, Insight, etc.).

The Role

We’re looking for a Senior Full-Stack LLM Engineer to help us evolve our community intelligence platform. You’ll build tools that transform peer knowledge into decision-making firepower—AI-enhanced, fast, and intuitive.

This is a high-leverage role for a builder who thrives on autonomy, ownership, and curiosity. You’ll work closely with our Head of Engineering, product team, and community operators to bring new experiences to life on the Braintrust for our community members. We are a remote-first company and considering candidates working from Central America and South America for this role.

Responsibilities

• Build, scale, and maintain end-to-end features across our web stack (React, Next.js, Node.js, Postgres, Vercel)

• Integrate AI-powered capabilities (e.g., summarization, semantic search, classification) into user-facing workflows

• Collaborate with design and product to deliver fast experiments and polished UX

• Write high-quality, tested, and observable code using modern development practices

• Contribute to architectural decisions and technical direction for a fast-growing product

• Leverage AI tools (e.g., Copilot, ChatGPT, Cursor) thoughtfully throughout your development workflow

• Maintain a culture of documentation, iteration, and extreme ownership

Requirements

• Production-level Python expertise, especially in API and backend service development

• 2+ years designing scalable APIs for chatbot integrations across platforms (Slack, web, mobile)

• 2+ years demonstrating advanced SQL and database design skills, including optimization for large-scale structured and unstructured data.

• 2+ years of hands-on experience with LLM orchestration frameworks (e.g., LangChain, Haystack, LlamaIndex, PromptQL, etc.)

• Strong foundation in algorithms and data structures; skilled in writing efficient, scalable code.

• Highly-proficient in RAG pipelines and vector databases (e.g. Pinecone, Weaviate, etc.)

• Highly-proficient in prompt engineering, multi-agent workflows, and fine-tuning models

• Highly-proficient in LLM caching and memory strategies to optimize token usage and response quality

• This role requires English proficiency at CEFR level B2 or above to collaborate effectively with our primarily English-speaking team.

Required Skills

• Python — Advanced
• SQL — Advanced
• LLM — Advanced
• RAG Pipeline — Intermediate
• LangChain — Intermediate
• Haystack — Intermediate
• LlamaIndex — Nice to have
• PromptQL — Nice to have

Benefits

• Fully Remote
• Flexible Hours
• Equity Compensation
• Remote Office Budget
• Paid Time Off
• Health Coverage

Compensation

$80K – $110K/year

Timezone: UTC-8 to UTC-3