AI Engineer

We re looking for an AI Engineer who gets excited about turning LLMs into reliable scalable systems that real users depend on If you ve battled retry logic at 3am debugged hallucinations in production or celebrated when your RAG system finally hit 95 accuracy we want to talk

You ll architect and deploy production-grade AI systems that solve real business problems Think customer intelligence agents automated sales workflows and RAG systems that actually retrieve the right context You ll work with modern frameworks like Lang Graph Llama Index or Vertex AI Agent Builder to build systems that scale from hundreds to thousands of daily users This isn t research it s engineering You ll own the full lifecycle designing architectures writing production code implementing robust error handling shipping to users and monitoring what matters

AI Systems Engineering

Hands-on experience deploying at least one AI system to production not just notebooks

Proficiency with LLM orchestration frameworks Lang Graph Llama Index AWS Agent Core or similar

Deep understanding of RAG architectures embeddings vector databases retrieval strategies

Experience with prompt engineering as an engineering discipline versioned tested and iterated

Production-quality Python with clean API design and proper error handling

Expertise in resilient systems retry logic exponential backoff circuit breakers

Testing strategies for non-deterministic systems yes we test our prompts

Async processing queue management and distributed systems patterns

Monitoring and observability for AI systems beyond just it works

Cost optimization for LLM-powered applications at scale

Deployment pipelines and feature flagging for gradual rollouts

Security practices including prompt injection prevention and PII handling

You’ve debugged why your RAG system retrieved irrelevant context and fixed the chunking strategy

You can explain the trade-offs between different vector databases for your use case

You’ve written tests that catch prompt regressions before they hit production

You think about AI systems in terms of latency, cost per query and accuracy metrics

You’ve had production incidents and learned from them

Built multi-agent systems with human-in-the-loop workflows

Integrated AI systems with CRM platforms Salesforce Hub Spot or business tools

Experience with evaluation frameworks for measuring LLM output quality

Open source contributions to AI tooling or framework projects

War stories about scaling AI systems from 100 to 10,000+ queries/day

Real Impact Your systems will process thousands of queries daily driving actual business outcomes

Modern Stack Work with cutting-edge AI frameworks and tools as they evolve

Ownership Own systems end-to-end from architecture to monitoring

Learning Culture Fast-moving AI landscape means constant learning and experimentation

Pragmatic Innovation Balance moving fast with building reliable maintainable systems

We re not looking for Pure ML researchers optimizing model architectures Data scientists building statistical models Prompt engineers without software engineering depth We are looking for Software engineers who ve fallen in love with building AI systems Builders who ship and iterate based on real user feedback Engineers who treat prompts like code and systems like products

Think this sounds like you Let s talk about the AI systems you ve built the production challenges you ve solved and what you want to build next We re building the future of AI-powered automation The question is will it work reliably at 3am when your users need it We think yes and we need engineers who know how to make that happen

AI Systems Engineering

Hands-on experience deploying at least one AI system to production (not just notebooks)

Proficiency with LLM orchestration frameworks (Lang Graph, Llama Index, AWS Agent Core, or similar)

Deep understanding of RAG architectures: embeddings, vector databases, retrieval strategies

Experience with prompt engineering as an…