AI Engineer

AvantStay, Inc.; United States; Remote; USD 170,000 - 260,000; Full time

Benefits offered by this job

Equity

Generous paid time off including all U

100% remote - work from anywhere in世界

Complimentary and discounted stays at数

Job summary

AvantStay is seeking a senior engineer to ship LLM-powered systems that integrate with PostgreSQL, ClickHouse, Kafka, and APIs. You will work closely with backend, frontend, data, and DevSecOps teams in a fully remote setup to build, maintain, and improve autonomous and human-in-the-loop AI solutions.

Ideal candidates have hands-on experience with distributed systems, strong TypeScript/Scala skills, and a proven ability to translate stakeholder needs into concrete features.

Qualifications

• Shipped at least one LLM-powered system used by real users
• Strong software engineering fundamentals — databases, Kafka, GraphQL/REST, Kubernetes, AWS
• Proficient in TypeScript; Scala and Python are a plus
• Product instincts and ability to walk out with a concrete idea of what to build
• Fluent in English
• Nice to have OSS contributions to AI ecosystem and functional programming background
• Experience with high-throughput data systems (Kafka, ClickHouse, Postgres at scale)

Responsibilities

• Ship LLM systems that tightly integrate with our infrastructure and knowledge bases
• Maintain autonomous and human-in-the-loop systems and ensure uptime and accuracy
• Interact with users and stakeholders to understand problems and design solutions
• Stay up-to-date with trends in LLMs and applied AI practices
• Collaborate with cross-functional team to create a product that solves real problems
• Update systems to be agent-accessible; refactor APIs for LLM usage
• Build tooling that lets engineering deploy agents faster

Skills

TypeScript

Scala

Python

Kubernetes

AWS

APIs

LLM systems

Observability

Tools

PostgreSQL

ClickHouse

Kafka

GraphQL/REST

Docker

Job description

Who we are

At AvantStay we run the technology platform behind 2,700+ vacation rentals across 60+ destinations. We’ve raised $200M+ of capital, do $250M+ in ARR, and have ~30 engineers building custom systems that price, list, market, and operate the entire portfolio. Recently we shipped multiple production AI agents, including a lead-qualification agent, on-demand BI reporting agent, CX agent and infrastructure monitoring agent that triages on-call alerts. We also are building an internal system to enable agentic evolution of our core products.

Our stack is Scala and TypeScript across the backend, PostgreSQL, ClickHouse, Kafka, Kubernetes on AWS. For AI we use Claude, OpenAI, LangGraph,, Openclaw and MCP servers we built ourselves.

The role

You will be a strong individual contributor comfortable working directly with stakeholders. You will be reporting to senior engineering leaders, working alongside ~30 people across backend, frontend, data, and DevSecOps. The team is fully remote, flat, and talent-dense. You won’t be starting from scratch - you’ll join a strong team with years of experience and strong understanding of our systems.

What you’ll do

• Ship LLM systems that tightly integrate with our infrastructure and knowledge bases: PostgreSQL, Clickhouse, Kafka, APIs, MCPs.

• Maintain autonomous and human-in-the-loop systems and ensure uptime and accuracy

• Interact with users and stakeholders to understand their problems and design solutions

• Stay up-to-date with the latest trends in LLMs and applied AI practices

• Collaborate with a cross-functional team of engineers, product managers, designers, and other members to create a product that solves actual problems.

• Update existing systems to be agent-accessible. Some % of the work is refactoring APIs that were never meant to be called by an LLM - be ready for that.

• Build the patterns and tooling that let the rest of engineering deploy agents faster.

What you’ve done before

• Shipped at least one LLM-powered system used by real users (internal or external) that took actions in a real system.

• Can talk specifically about evals, retrieval shape, observability of agent traces, and handling non-determinism in a system business operators depend on.

• Strong software engineering fundamentals - databases, Kafka, GraphQL/REST, Kubernetes, AWS.

• Proficient in TypeScript. Scala (functional, Typelevel) and Python are a plus, but deep Scala expertise is not required.

• Product instincts. You can sit with a stakeholder for an hour and walk out with a concrete idea of what to build.

• Fluent in English.

Nice to have

• OSS contributions to the AI ecosystem. Examples: LangGraph, PydanticAI, DSPy, instructor, or similar.

• Functional programming background. Preference to use functional paradigm.

• High-throughput data systems experience (Kafka, ClickHouse, Postgres at scale).

Perks and Benefits

• Equity

• Generous paid time off including holidays

• 100% remote - work from anywhere in the world

• Complimentary and discounted stays at AvantStay properties

• Periodic team gatherings

• Budget for Greenfield AI Tooling