About This Role
This role involves owning the machine learning systems behind Hirivo, focusing on job-matching, ranking models, and LLM agents for reading job adverts and filling application forms. It suits an engineer who will take features from prototype to production, then measure and monitor their performance within a small applied-AI team.
Responsibilities
- Build and improve LLM-powered agents that read job adverts and application forms and complete them accurately from a candidate's profile and CV (tool use, multi-step workflows, handing questions to the candidate when needed)
- Build job-to-candidate matching and ranking using embeddings, retrieval (RAG) and vector search, behind the campaign match score
- Create evaluation sets and automated evals for form-fill accuracy, match quality and agent success rate, then iterate on prompts, models and fine-tunes
- Train, fine-tune and benchmark models (PyTorch), for example to parse CVs and job descriptions and to classify job fit
- Deploy models and agents as scalable APIs and services on the cloud (AWS/GCP) with Docker, Kubernetes and CI/CD, integrated with our Node backend
- Add observability: tracing of agent runs, latency/cost dashboards, failure and drift monitoring
- Build data pipelines that collect and clean job listings from many sources
- Work with product and with candidates to turn real job-seeker problems into shipped features, and care about responsible AI: candidates' data, fairness and accuracy
Requirements
- Strong Python and solid software-engineering fundamentals (APIs, backend services, testing)
- Hands-on experience building with LLMs: OpenAI/Anthropic APIs, prompting, agents or RAG
- Experience shipping ML or AI systems to production and running them at scale
- Experience training and evaluating models, plus familiarity with PyTorch
- Cloud experience (AWS, GCP or Azure) plus Docker/Kubernetes
- A degree in Computer Science or a related field, or equivalent experience
- A product mindset: you care about users and measurable impact
Nice to have:
- Building LLM evaluation frameworks (evals, benchmarks, LLM-as-judge)
- Monitoring and observability tooling (e.g. Datadog, OpenTelemetry, LangSmith)
- Open-source contributions or a public portfolio of AI projects
- A second language such as TypeScript, Go, C++ or Rust
- GPU / CUDA / inference-performance optimisation
- Fine-tuning (LoRA, RLHF/DPO)
- Familiarity with AI safety or responsible AI
- Recommender/ranking systems, MLOps tooling (MLflow, model registry), web scraping/data pipelines
Benefits