AI Engineer

Job not on LinkedIn

🕒 July 13

🇺🇦 Ukraine – Remote

⏰ Full Time

🟡 Mid-level

🟠 Senior

🤖 AI Engineer

👻 Ghost score 29%

What it means: how likely this posting is sitting open without active hiring.How to read it: 60% or higher means we think this is a ghost. Lower scores are less of a worry.How we score it: age, reposts, open roles vs team size, how fast jobs close, and whether pay is listed.Fine print: an estimate from public data, not a judgment of the company. Real jobs can score high, so treat it as a hint, not a fact.

Apply Now

Find Similar Remote Jobs

Set Up Email Alert For New Jobs

📊 Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Upload Resume

Lvivity

WebsiteLinkedInAll Job Openings

51 - 200 employees

Founded 2013

💼 Consulting

📣 Marketing

Consulting • Marketing • Software Development

Lvivity is a software development and outsourcing company that specializes in creating efficient and scalable products using the latest web and mobile technologies. They offer a wide range of services including web development, mobile development, desktop development, MVP development, IT and software consulting, and UI/UX design. With a customer-oriented approach, Lvivity focuses on understanding and achieving the goals of their clients, offering flexibility, and transparency in their development process. They have experience in handling projects of varying complexity and have been recognized for their outstanding custom software development services for over 7 years.

📋 Description

• Own the analysis engine, including attributes and scoring rules that determine whether a model understands a business • Monitor model behavior changes and update analysis rules accordingly • Build and maintain the evaluation framework with ground-truth sets, metrics, and regression detection • Develop retrieval for real websites, including text extraction, chunking, embedding-model selection, and source traceability for claims • Design the agentic architecture and justify choices based on cost and latency • Benchmark frontier models against open-weight models and route requests based on answer impact and cost • Implement guardrails and observability for input/output validation, prompt-injection resistance, hallucination detection, tracing, cost attribution, and latency monitoring • Read and apply research on LLM and GEO behavior, translating findings into production code and evidence-based changes • Work daily in a Python stack using FastAPI, PostgreSQL, and pytest

🎯 Requirements

• Production Python; daily use of FastAPI, PostgreSQL, and pytest • Direct experience with LLM SDKs • Understanding of when orchestration frameworks such as LangChain, LangGraph, or Pydantic AI stop paying for themselves • Production retrieval experience, including extraction, chunking, embedding-model selection, recognizing when retrieval is not the answer, and vector stores such as pgvector or Qdrant • Proper LLM-system evaluation using real datasets, metrics beyond exact match, and judges checked against human labels • Familiarity with Langfuse, Promptfoo, or Ragas • Ability to form and test hypotheses about retrieval or ranking behavior • Prompt, context, and harness engineering experience; familiarity with DSPy is an example • Experience designing agentic systems and explaining architectural choices • Experience operating agentic systems in production, including tracing, token and cost attribution, latency, and error-rate monitoring • Familiarity with Langfuse, LangSmith, or Prometheus • Understanding of adversarial system failures, including prompt injection, plausible but false outputs, and validation methods • Familiarity with Guardrails AI, LLM Guard, or NeMo Guardrails • Nice to have: SEO, generative engine optimisation (GEO), or search-visibility products • Nice to have: classical NLP, including classification, named entity recognition, and sentiment analysis • Nice to have: WordPress, CMS integrations, schema.org, or llms.txt • Nice to have: crawling and extraction at scale, including JavaScript rendering, rate limits, and content quality • Nice to have: AI governance and risk management practice, such as the EU AI Act • Three-month probation period

🏖️ Benefits

• Full medical insurance • MacBook & accessories • English lessons • Accountant assistance • Annual paid vacation — 20 working days • 7 unconfirmed sick days/days off a year • Flexible work schedule • Remote work option • Hybrid work option combining on-site work in the Lviv office and remote work • Minimal bureaucracy, synergy, and formalities, primarily focusing on effective communication