About The Position

Bolder Apps is hiring an ML Engineer to own the AI side of client products. The role involves designing and shipping production LLM features, including chat assistants, knowledge search, safety checks, and evaluation systems. The first project is a healthcare AI product in a regulated environment where safety, privacy, and data residency are important; subsequent work will involve similar AI projects for other clients. The engineer will select models based on test results, review AI code, and explain technical decisions to non-technical clients. This is a full-time, in-house role on the Bolder Apps team, open to people based in the countries listed in the post. Bolder Apps is a product development studio partnering with US-based startups and established companies to build and scale digital products. The company specializes in AI-powered development, full-cycle product creation, and engineering team augmentation. Its culture emphasizes speed, ownership, autonomy, collaboration, and bringing ideas forward.

Requirements

  • At least 4 years of experience in software engineering or ML, including at least 2 years building LLM applications used by real users; prototypes and demos alone do not count.
  • Strong Python skills.
  • Hands-on experience with production RAG, including embeddings, hybrid search, reranking, and vector databases.
  • Experience with prompt and context engineering and multi-step chat flows, such as orchestration or agents, with streaming replies.
  • Experience building test sets and automated quality checks and using them to compare models on quality, speed, and cost.
  • AI safety experience, including guardrails, safety classifiers, content moderation, and prompt-injection protection.
  • Comfort working in a TypeScript/Node.js codebase alongside the backend team.
  • Ability to explain model choices and trade-offs to non-technical clients in plain language.
  • Good spoken and written English; the role involves writing design documents and joining client technical calls.
  • Use of AI tools every day in an AI-augmented engineering workflow.

Nice To Haves

  • Arabic speaker, or experience building LLM products in Arabic or other non-English languages.
  • NestJS experience.
  • Fine-tuning with LoRA or QLoRA and self-hosting models on GPUs, for example with vLLM.
  • Speech-to-text, text-to-speech, or voice AI experience.
  • Experience with healthcare, mental health, or other regulated data, including data residency rules.
  • Azure experience, especially Azure AI Foundry.

Responsibilities

  • Own the AI design for client projects, including chat flows, knowledge search, safety checks, model selection, and testing.
  • Build retrieval-augmented generation (RAG) pipelines using embeddings, hybrid search, reranking, PostgreSQL, and pgvector.
  • Design prompts, context, and multi-step chat flows, including agents, tool use, and streaming replies.
  • Work with open-weight models such as Qwen, Llama, and Gemma, served through LiteLLM or another OpenAI-compatible gateway and Azure AI Foundry.
  • Build evaluation systems, including test sets, automated quality checks, and side-by-side model comparisons for quality, speed, and cost.
  • Implement safety measures such as guardrails, safety classifiers, content moderation, and prompt-injection protection.
  • Choose models based on test results and explain the decision clearly to non-technical clients.
  • Review AI code from other developers and set standards for building with LLMs.
  • Join client technical calls and answer client questions about AI.

Benefits

  • Autonomy and trust without daily checklists or micromanagement.
  • A team ready to help employees grow.
  • Ownership of AI design on real products in a regulated space.
  • A steady pipeline of AI projects after the first project.
  • Ownership of model choice and architecture without a rigid playbook.
  • Direct access to decision-makers.
  • A peer network of engineers, designers, and project managers working on overlapping projects.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service