About Joveo
Every company says they're "AI-first." We actually are. Joveo's recruitment advertising platform processes millions of hiring decisions through machine learning, real-time bidding, and predictive analytics — helping the world's largest employers find the right people, faster and fairer. But we're not done. Not even close.
Role Overview
We are hiring an LLM Engineer to build production-grade AI systems powered by large language models at the core of Joveo's platform. You will architect RAG pipelines, evaluation systems, and LLM-powered features that bring a new level of intelligence to how employers and job seekers connect.
Key Responsibilities
- Design and build LLM-powered applications including RAG systems and agentic workflows
- Fine-tune, evaluate, and optimize LLMs for domain-specific recruitment tasks
- Build prompt engineering frameworks and manage prompt versioning at scale
- Develop evaluation and benchmarking pipelines for LLM quality and safety
- Integrate LLM capabilities with production APIs, databases, and internal systems
- Monitor LLM behavior in production — latency, cost, hallucination, and output quality
Required Skills & Qualifications
- Deep hands-on experience building LLM applications in production
- Proficiency with LLM frameworks — LangChain, LlamaIndex, DSPy, or similar
- Experience with RAG architectures, vector databases (Pinecone, Weaviate, pgvector)
- Familiarity with OpenAI, Anthropic, Google, or open-source model APIs
- Experience with LLM evaluation — RAGAS, custom benchmarks, human preference data
- Strong Python skills and software engineering fundamentals