Responsibilities
- Design, implement, and maintain end-to-end AI applications, including chatbots, Q&A platforms, and agent workflows
- Collaborate directly with clients to understand their needs, identify opportunities, and recommend LLM-driven solutions
- Develop and manage robust data pipelines, prompt strategies, and datasets to ensure effective and accurate AI models (Will be +)
- Evaluate and refine AI system performance, ensuring outputs are accurate, secure, scalable, and compliant with industry regulations (Will be +)
- Conduct research and rapid prototyping to validate technical feasibility and demonstrate the business value of AI solutions
- Stay current with evolving LLM technologies, frameworks, and methodologies to continuously improve solutions and client outcomes
Basic qualifications
- Strong proficiency in Python, experience with web frameworks like FastAPI or similar
- Understanding of the AI application development lifecycle
- Experience with rapid UI prototyping using Streamlit, Gradio, or similar frameworks
- Familiarity with major LLM platforms and APIs (OpenAI, Anthropic, Amazon Bedrock, Gemini) and related frameworks (LangGraph, LlamaIndex, Strands Agents, etc.)
- Knowledge of advanced AI integration patterns (e.g., RAG, Agents)
- Experience deploying AI solutions at scale, with considerations for performance, cost-efficiency, and maintainability
- Proven ability to evaluate generative AI quality using metrics such as retrieval and classification scores, as well as LLM-based evaluation methods
- Proven experience in AI engineering and delivering ML-based solutions
- Strong problem-solving skills and attention to detail
- Excellent communication, collaboration, and interpersonal skills
Preferred qualifications
- Experience designing experiments, conducting A/B tests, and iterating on models based on user feedback
- Understanding of retrieval systems (keyword search, vector search, embeddings) and ranking algorithms
- Familiarity with emerging protocols such as MCP, A2A, ACP, etc.
- Experience deploying to cloud AI platforms (Azure OpenAI, Amazon Bedrock, GCP Vertex AI) or on-premise solutions (e.g., vLLM)
- Experience with enterprise AI platforms such as AWS AgentCore or Databricks AgentBricks or Google Agents Space, or Azure AI Foundry
- Experience with observability and monitoring tools and frameworks
- Opportunity to work in a fast-paced, agile, software engineering culture
- Comfortable modern office in Prague 7, with support of hybrid or fully remote mode
- Benefit program (5 weeks of vacation, paid sick days, paid days off for special occasions, meal vouchers, flexi pass, Prague city public transport annual coupon, multisport cards, optional contribution to pension fund, health insurance for family member)
- EPAM Employee Stock Purchase Plan (ESPP) (subject to certain eligibility requirements)
- English language courses
- Czech language courses upon request
- Referral bonuses for recommended candidates
- Mobile Phone Tariff’s program for managerial-level candidates
- Great learning and development opportunities, including in-house professional training, career advisory and coaching, sponsored professional certifications, well-being programs, LinkedIn Learning Solutions and much more
Tags & focus areas
Used for matching and alerts on DevFound Remote Ai Ai Engineer Generative Ai