About this ML Engineer (AI / LLM) role at Bolder Apps
We're hiring an ML Engineer to own the AI side of the products Bolder Apps builds for clients. You'll design and ship LLM features that real people use every day: chat assistants, knowledge search, safety checks, and the tests that prove a model is good enough before it goes live. Your first project is an AI product in healthcare, a regulated space where safety, privacy and data residency really matter. After that, you'll lead similar AI projects for other clients. You'll choose models based on real test results, review AI code from other developers, and explain your choices to clients who are not technical. This is a full-time, in-house role on the Bolder Apps team, open to people based in the countries listed in this post. If you've taken LLM features past the prototype stage and into production, and you care as much about safety and evaluation as about clever prompts, we want to talk.
About Us
Bolder Apps is a product development studio that partners with US-based startups and established companies to build and scale innovative digital products. We specialize in AI-powered development, full-cycle product creation, and engineering team augmentation. Our mission is simple: build bolder, faster, and smarter.
Our Culture & Values (read before applying)
We move fast. We take ownership. We work with AI, not against it. And we expect everyone to bring ideas, not wait for instructions.
There are no daily checklists, no micromanagement, and no corporate politics. Instead, you'll have autonomy, trust, and a team that's always ready to help you grow. At Bolder Apps, impact matters more than titles, and curiosity matters more than seniority.
If you want a place where you can level up fast and actually see your work making a difference - welcome aboard.
Responsibilities
- Own the AI design on client projects: chat flows, knowledge search, safety checks, model choice and testing
- Build retrieval (RAG) pipelines with embeddings, hybrid search and reranking on PostgreSQL with 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: test sets, automated quality checks, and side-by-side model comparisons on quality, speed and cost
- Put safety in from day one: guardrails, safety classifiers, content moderation and protection against prompt injection
- Pick the right model from test results and explain the choice clearly to a non-technical client
- Review AI code from other developers and set the standard for how we build with LLMs
- Join client technical calls and answer their AI questions directly
Nice to have
- Arabic speaker, or experience building LLM products in Arabic or other non-English languages (a big plus)
- NestJS experience
- Fine-tuning with LoRA or QLoRA, and self-hosting models on GPUs (for example vLLM)
- Speech to text, text to speech or voice AI
- Healthcare, mental health or other regulated data, including data residency rules
- Azure, especially Azure AI Foundry
Requirements
- 4+ years in software engineering or ML, with at least 2 years building LLM applications that real users use. Prototypes and demos alone don't count
- Strong Python
- Hands-on RAG in production: embeddings, hybrid search, reranking and vector databases
- Prompt and context engineering, plus multi-step chat flows (orchestration, agents) with streaming replies
- Real evaluation work. You've built test sets and automated quality checks and used them to compare models on quality, speed and cost
- AI safety experience: guardrails, safety classifiers, content moderation and prompt-injection protection
- Comfortable working in a TypeScript / Node.js codebase alongside the backend team
- You can explain a model choice and its trade-offs to a non-technical client in plain words
- Good spoken and written English. You'll write design docs and join client technical calls
- AI-augmented workflow. You use AI tools every day in your own engineering work
Benefits
- Full-time, in-house role on the Bolder Apps team
- Own the AI design on real products in a regulated space, not toy demos
- Steady pipeline of AI projects after the first one
- Real ownership over model choice and architecture, with no rigid playbook
- Direct line to decision-makers, no extra layers between you and the people who own the outcome
- A peer network of engineers, designers and PMs working on overlapping projects