ML Engineer (AI / LLM)
New
B
Bolder AppsAI software
Open to people based in the countries listed in this post: Tashkent, Tashkent, Uzbekistan. Georgia. Argentina. Mexico. ColombiaFull-TimeMiddle
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Languages
- Good spoken and written English. Arabic speaker, or experience building LLM products in Arabic or other non-English languages (a big plus)
- Experience
- 4+ years in software engineering or ML, with at least 2 years building LLM applications that real users use.
- Required Skills
- Node.jsPythonTypeScriptPrompt Engineering
Requirements
- Have 4+ years of experience in software engineering or ML.
- Have at least 2 years building LLM applications used by real users; prototypes and demos alone do not count.
- Have strong Python skills.
- Have hands-on experience with production RAG, including embeddings, hybrid search, reranking, and vector databases.
- Know prompt and context engineering and multi-step chat flows, including orchestration or agents and streaming replies.
- Have built test sets and automated quality checks, and used them to compare models on quality, speed, and cost.
- Have AI safety experience with guardrails, safety classifiers, content moderation, and prompt-injection protection.
- Be comfortable working in a TypeScript/Node.js codebase alongside a backend team.
- Be able to explain model choices and trade-offs to non-technical clients in plain language.
- Have good spoken and written English for design documents and client technical calls.
- Use AI tools every day in your own engineering work.
Responsibilities
- Own the AI design on client projects, including 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.
- Implement safety measures including guardrails, safety classifiers, content moderation, and protection against prompt injection.
- Choose models based on test results and explain the choice clearly to non-technical clients.
- Review AI code from other developers and set standards for building with LLMs.
- Join client technical calls and answer their AI questions directly.
View Full Description & ApplyYou'll be redirected to the employer's site