|
Описание: |
Our client
WebPros, the largest web hosting software and automation company, manages 900,000+ servers, 85 million domains, and 33 million users. WebPros unites top providers in web hosting, billing automation, infrastructure, server management, and online marketing software. Currently, their lineup includes cPanel, Plesk, SolusVM, WHMCS, XOVI NOW, Sitejet, 360 Monitoring, and koality, with ongoing additions.
Job Description
Join our global Data&AI team at WebPros, where you will play a crucial role in operationalizing and optimizing Large Language Model (LLM) solutions. As an AI Operations Engineer, you will work closely with cross-functional teams to design prompts, implement safety guardrails, and ensure traceability and monitoring of generative AI systems. Your expertise will help drive innovation and safe deployment of AI technologies across the organization.
Responsibilities
As an AI Operations Engineer, your key responsibilities will include:
· Design, test, and validate prompts using techniques such as zero-shot, few-shot, chain-of-thought, and agentic prompting
· Collaborate with teams to optimize prompts for performance, accuracy, and safety.
· Implement guardrails using input/output validation mechanisms including prompt injection prevention, toxicity filtering, and hallucination detection.
· Setup and configure LLMOps platforms to orchestrate, monitor, safeguard and optimize the use of LLMs within our applications.
· Support AI risk assessments and compliance efforts.
· Work with SDKs (e.g., LangChain) and APIs to integrate LLMs into products and services.
· Explore fine-tuning techniques such as system prompt tuning and retrieval-augmented generation (RAG).
Qualifications
To be successful in this role, candidates should have:
· Strong technical background with proficiency in Python and experience working with LLM APIs and SDKs (e.g. LangChain, Semantic Kernel, Haystack).
· Hands-on experience with prompt engineering and LLM orchestration tools.
· Familiarity with AI guardrailing techniques.
· Experience with monitoring, logging, and traceability in AI systems.
· Ability to work cross-functionally and communicate complex AI concepts clearly.
· Exposure to LLMOps platforms (e.g., Langfuse, LangSmith, PromptLayer).
· Understanding of post-training techniques like RAG or system prompt fine-tuning.
· Knowledge of AI governance and risk management practices.
· English language proficiency (B2/C1 level)
· Experience setting up and working with MCP/A2A is a plus
Social package & benefits:
— Full medical insurance
— MacBook & accessories
— English lessons
— Accountant assistance
— Minimal bureaucracy, synergy, and formalities, primarily focusing on effective communication
Відгукнутись на вакансію |
