Senior AI Engineer (LLM)Role OverviewWe are hiring a Senior AI Engineer with deep LLM expertise and strong software engineering skills to build and ship a production AI system that evaluates luxury goods from photos. You will own core model and pipeline work end-to-end, from prompt and model design through evaluation, deployment, and monitoring.
About the Product

Our client is building an AI-powered authentication and valuation assistant for the pre-owned and resale luxury market. Users upload photos of a designer item, and the system analyzes visual details to estimate a maximum fair price and flag signs that an item may be counterfeit. The goal is to give buyers the confidence to tell genuine goods from fakes before they spend money.

The product combines multimodal LLMs, computer vision, and market-pricing signals, and it must be accurate, explainable, and fast enough for consumer use.

Responsibilities

Design, build, and optimize LLM and multimodal pipelines that analyze item photos and produce authenticity assessments and price estimates.
Develop prompting, retrieval-augmented generation (RAG), fine-tuning, and agentic workflows to improve accuracy and reduce hallucinations.
Build evaluation frameworks and benchmarks, including labeled datasets, regression tests, and metrics for authenticity detection and pricing error.
Integrate vision models and LLMs into scalable, low-latency production services with solid APIs.
Manage cost, latency, and reliability trade-offs across model providers and self-hosted options.
Monitor model performance in production, investigate failure cases, and iterate quickly on improvements.
Collaborate with product, data, and engineering teammates, and contribute to technical design and code reviews.
Document architecture, experiments, and decisions clearly.

Required Qualifications

6+ years of professional experience in AI/ML or software engineering, with at least 4 years building production applications on LLMs.
Deep, hands-on LLM expertise: prompt engineering, RAG, fine-tuning (e.g., LoRA/PEFT), function calling, and evaluation of LLM outputs.
Experience with multimodal or vision-language models (image understanding) and working with image data.
Strong software engineering foundations: expert Python, clean and testable code, system design, APIs, and CI/CD.
Experience deploying and operating ML services in production on a major cloud platform (AWS, GCP, or Azure), including Docker and observability.
Proven ability to design rigorous evaluation setups and make data-driven decisions on model quality.
Experience with LLM tooling such as PyTorch, Hugging Face, LangChain or LlamaIndex, and vector databases.
Excellent written and spoken English; comfortable working independently and asynchronously in a remote team.

Nice to Have

Experience in fraud detection, authentication, anomaly detection, or fine-grained image classification.
Background in e-commerce, marketplace, resale, or luxury and fashion domains.
Experience with price prediction, valuation, or recommendation models.
Familiarity with LLM evaluation and observability tools, and with inference optimization (quantization, batching, caching).
Contributions to open-source AI projects or published technical work.

Engagement Details