Senior AI/ML Engineer

EPAM Systems; Deutschland; Vor Ort; EUR 75.000 - 95.000; Vollzeit

Zusammenfassung

EPAM Systems is seeking a Senior AI/ML Engineer responsible for designing and optimizing generative AI solutions. The role requires expertise in applications utilizing large language models and background in prompt engineering strategies.

This position is ideal for those proficient in Python and familiar with cloud-based AI services, with the added advantage of experience in specific industries such as finance or life sciences.

Qualifikationen

• Background in developing applications with generative AI models.
• Expertise in prompt engineering and RAG architecture.
• Proficiency in Python, with experience in asynchronous applications preferred.

Aufgaben

• Design applications utilizing large language models and generative AI technologies.
• Implement prompt engineering strategies and RAG architectures.
• Build frameworks to evaluate model performance, safety, and alignment.

Kenntnisse

Developing applications with generative AI models

Prompt engineering

RAG architecture

Proficiency in Python

Knowledge of modern AI/ML frameworks

Familiarity with vector databases

Understanding of responsible AI practices

Competency with cloud-based AI services

Jobbeschreibung

We are seeking a Senior AI/ML Engineer who will be responsible for designing, implementing, and optimizing generative AI solutions for applications.

Responsibilities

• Design applications utilizing large language models (LLMs) and generative AI technologies
• Implement prompt engineering strategies and Retrieval-Augmented Generation (RAG) architectures
• Build frameworks to evaluate model performance, safety, and alignment
• Create interfaces between generative AI models and production systems
• Develop mechanisms for responsible AI and guardrails for deployment
• Stay updated on advancements in generative AI research and best practices

Requirements

• Background in developing applications with generative AI models
• Expertise in prompt engineering and RAG architecture
• Proficiency in Python, with added value for experience in asynchronous applications
• Knowledge of modern AI/ML frameworks (e.g., LangChain)
• Familiarity with vector databases and embedding models
• Understanding of responsible AI practices and mitigation strategies for hallucinations
• Competency in working with cloud-based AI services (e.g., OpenAI API, Azure AI)

Nice to have

• Background in developing solutions for specific industries such as life sciences, finance, or insurance
• Familiarity with LLM tracing, evaluation datasets, and experiment management
• Understanding of techniques for evaluating RAG systems or other LLM architectures
• Skills in automated prompt optimization tools (e.g., dspy)
• Expertise in creating rapid prototypes