AI Engineer

Rozafa Consulting is growing fast, and we’re looking for an
**AI Engineer**
who loves building real software and applying AI to production systems.

This role will contribute to features on our company owned and operated apps as well as client feature requests.

If you’re excited about shipping intelligent features used by thousands of users—this role is for you.

 What you’ll do

- Develop and integrate LLM-powered features such as AI-assisted workflow automation, code generation, and content strategy.
- Optimize AI performance through prompt engineering, retrieval-augmented generation (RAG), and evaluation frameworks.
- Build and scale AI infrastructure, ensuring low-latency responses, caching, and cost-efficient model usage.
- Implement AI observability and safeguards, monitoring quality, security, and compliance.
- Collaborate with product and engineering teams to deliver intuitive, AI-driven user experiences.
- Stay ahead of AI advancements, continuously improving our AI-powered capabilities.
- Collaborate with early adopters to optimize model performance and usability.
- Collaborate on system architecture and technical decisions
- Contribute to non-AI software features when needed

What we’re looking for

- 3+ years of experience in machine learning engineering, AI/LLM integration, or applied NLP
- Proven track record of building LLM-powered applications
- Strong experience with foundation models (GPT-4o, Claude, etc.) and advanced prompt engineering
- Experience with embedding models (e.g., OpenAI Ada, Cohere, or local vector stores like pgvector, Weaviate, Pinecone)
- Deep understanding of retrieval-augmented generation (RAG) and contextual AI response optimization
- Familiarity with LangChain, or similar frameworks for orchestrating LLM-powered applications
- Strong programming skills in Typescript (experience with AI frameworks like Hugging Face, LangChain, MCP, or OpenAI SDK)
- Experience in evaluating LLM performance, running A/B tests, and implementing feedback loops for AI refinement
- Solid understanding of caching, rate limiting, and cost optimization strategies for AI workloads
- Ability to work cross-functionally with engineers, product managers, and end users to develop impactful AI solutions
- Good communication skills

What we offer

- Competitive salary (based on experience)
- Remote / hybrid work options
- Work on
**AI projects and core software features**
- Strong engineering culture and modern tech stack
- Growth in AI systems, architecture, and leadership
- Products used at scale, locally and internationally