AI Engineer - AI/LLM (Backend)

The company is focused on building advanced Generative AI and LLM-based solutions for businesses across industries such as healthcare, finance, legal, and tech.

They work on intelligent automation, custom AI systems, and improving LLM accuracy for complex real-world use cases. The team is international, with 3000+ professionals globally, and the environment is highly innovation-driven and collaborative.

We are hiring a mid-level AI Engineer to build and ship AI-powered features end-to-end. 

This is not a junior role - candidates must have hands-on experience delivering production-ready AI solutions and the ability to independently execute in a fast-paced environment. 

You will work closely with founders and product teams to develop intelligent systems such as copilots, chatbots, and automation tools, while ensuring performance, scalability, and reliability. 

Key Responsibilities 

• Build and ship AI-powered features (chatbots, copilots, automation tools)  
• Design and implement RAG pipelines using embeddings and vector search  
• Write and optimize prompts and system instructions  
• Integrate LLM APIs (OpenAI, Anthropic, etc.) into production systems  
• Develop backend services (Python / Node.js) to support AI workflows  
• Work with real-world data (documents, logs, APIs)  
• Improve system reliability through evaluations, testing, and iteration  
• Debug issues such as hallucinations, latency, and cost inefficiencies  
• Collaborate closely with founders and product team on product direction  

Requirements 

• 2+ years of experience in Machine Learning or AI-related roles  
• Strong coding skills in Python or JavaScript  
• Hands-on experience working with LLM APIs  
• Experience building RAG pipelines or agent-based systems  
• Solid understanding of ML fundamentals (fine-tuning is a plus)  
• Proven ability to build and ship production-ready systems  

Tech Stack 

• Python, Node.js  
• OpenAI / Anthropic APIs  
• Vector databases (Pinecone, Chroma)  
• React / Next.js  
• AWS / Vercel  
• LangChain / LlamaIndex  
• Prompt engineering  
• Embeddings + vector search  
• API design and backend systems  

Nice to Have 

• Experience with LLM evaluation, fine-tuning, or model optimization  
• Exposure to agent frameworks or multi-step reasoning systems  
• Domain experience in finance, healthcare, legal, or other high-accuracy environments