Prompt Engineer

Jobtailor; Deutschland; Remote; EUR 70.000 - 110.000; Vollzeit

Zusammenfassung

Jobtailor is seeking a senior AI prompts engineer to create and optimize prompts for text, image, audio, and multimodal models in complex business contexts. You will design reusable prompt libraries, develop structured prompts, and collaborate with Product, Software, Data, and Security teams to ensure scalable, compliant AI solutions.

Applicants should have deep experience with LLMs, RAG, JSON Schema, and API integrations, and possess strong technical English.

Qualifikationen

• Advanced experience with LLMs and multimodal models.
• Strong command of prompt engineering techniques.
• Knowledge of Python or another programming language.
• Experience with AI model APIs.
• Knowledge of RAG, embeddings, vector databases, and semantic search.
• Familiarity with agents, function calling, and workflow orchestration.
• Understanding of machine learning, natural language processing, and model evaluation.
• Experience with JSON Schema, REST APIs, databases, and distributed systems.
• Knowledge of observability, automated testing, and version control.
• Understanding of cloud computing.
• Knowledge of DevOps and MLOps is a plus.
• Experience in sectors such as Finance, Legal, Healthcare, Customer Service, or Technology is a plus.
• Participation in AI projects deployed to production is a plus.
• Experience with human evaluation and test dataset creation is a plus.
• Knowledge of fine-tuning, LoRA, and supervised training is a plus.
• Experience with LLM observability and evaluation platforms is a plus.
• Knowledge of AI application security is a plus.
• Advanced technical English is a plus.
• Proven track record of reducing costs, improving accuracy, or delivering measurable automation is a plus.

Aufgaben

• Create, test, and optimize prompts for text, image, audio, and multimodal models.
• Develop simple, chained, parameterized, and tool-use-oriented prompts.
• Design structures for personas, context, few-shot prompting, structured reasoning, classification, extraction, generation, function calling, APIs, and information retrieval.
• Create reusable libraries of prompts, templates, and AI components.
• Adapt prompts to different models, providers, languages, and use cases.
• Translate product and business requirements into LLM-based solutions.
• Participate in building agents, chatbots, copilots, and intelligent automations.
• Design conversational and decision-making flows.
• Integrate AI models with APIs, databases, enterprise systems, and external tools.
• Work with RAG architectures, tool-using agents, multi-step workflows, conversational memory, classification, and routing.
• Create test suites and benchmarks to evaluate prompts.
• Define metrics for accuracy, relevance, consistency, completeness, hallucination rate, format adherence, latency, and cost per execution.
• Compare models and prompting strategies; conduct standard, edge-case, ambiguous, and adversarial testing.
• Implement continuous evaluation in production; analyze failures and adjust prompts, contexts, data, and validation rules.
• Identify and mitigate risks related to prompt injection, information leakage, inappropriate content, unauthorized responses, tool misuse, and data exposure.
• Create safety instructions, refusal rules, and operational boundaries.
• Apply Brazil’s LGPD, privacy principles, and AI governance practices.
• Define mechanisms for response validation, filtering, and auditing.
• Support responsible AI use policies.
• Structure documents, metadata, and knowledge bases for AI use.
• Support document segmentation, indexing, and retrieval.
• Evaluate the quality, currency, and reliability of sources.
• Design structured input and output formats, especially JSON and JSON Schema.
• Collaborate with Product, Software Engineering, Data, Security, Legal, and business teams.
• Interview users and subject-matter experts; document decisions, standards, versions, and experiment results.
• Mentor engineers, analysts, and junior professionals.
• Communicate technical limitations, risks, and results to non-technical audiences.
• Monitor models in production and identify performance changes.
• Manage prompt and configuration versioning.
• Optimize cost, speed, stability, and scalability.
• Create fallback, human review, and error-handling mechanisms.
• Keep up to date with developments in models, frameworks, and generative AI techniques.

Kenntnisse

LLMs

Multimodal models

Prompt engineering

Python

AI model APIs

RAG

Embeddings

Vector databases

REST APIs

JSON Schema

Automation testing

Version control

Cloud computing

MLOps

Databases

Tools

APIs

Databases

Distributed systems

Cloud computing

Jobbeschreibung

• Create, test, and optimize prompts for text, image, audio, and multimodal models
• Develop simple, chained, parameterized, and tool-use-oriented prompts
• Design structures for personas, context, few-shot prompting, structured reasoning, classification, extraction, generation, function calling, APIs, and information retrieval
• Create reusable libraries of prompts, templates, and AI components
• Adapt prompts to different models, providers, languages, and use cases
• Translate product and business requirements into LLM-based solutions
• Participate in building agents, chatbots, copilots, and intelligent automations
• Design conversational and decision-making flows
• Integrate AI models with APIs, databases, enterprise systems, and external tools
• Work with RAG architectures, tool-using agents, multi-step workflows, conversational memory, classification, and routing
• Create test suites and benchmarks to evaluate prompts
• Define metrics for accuracy, relevance, consistency, completeness, hallucination rate, format adherence, latency, and cost per execution
• Compare models and prompting strategies; conduct standard, edge-case, ambiguous, and adversarial testing
• Implement continuous evaluation in production; analyze failures and adjust prompts, contexts, data, and validation rules
• Identify and mitigate risks related to prompt injection, information leakage, inappropriate content, unauthorized responses, tool misuse, and data exposure
• Create safety instructions, refusal rules, and operational boundaries
• Apply Brazil’s LGPD, privacy principles, and AI governance practices
• Define mechanisms for response validation, filtering, and auditing
• Support responsible AI use policies
• Structure documents, metadata, and knowledge bases for AI use
• Support document segmentation, indexing, and retrieval
• Evaluate the quality, currency, and reliability of sources
• Design structured input and output formats, especially JSON and JSON Schema
• Collaborate with Product, Software Engineering, Data, Security, Legal, and business teams
• Interview users and subject-matter experts; document decisions, standards, versions, and experiment results
• Mentor engineers, analysts, and junior professionals
• Communicate technical limitations, risks, and results to non-technical audiences
• Monitor models in production and identify performance changes
• Manage prompt and configuration versioning
• Optimize cost, speed, stability, and scalability
• Create fallback, human review, and error-handling mechanisms
• Keep up to date with developments in models, frameworks, and generative AI techniques

Requirements

• Advanced experience with LLMs and multimodal models
• Strong command of prompt engineering techniques
• Knowledge of Python or another programming language
• Experience with AI model APIs
• Knowledge of RAG, embeddings, vector databases, and semantic search
• Familiarity with agents, function calling, and workflow orchestration
• Understanding of machine learning, natural language processing, and model evaluation
• Experience with JSON Schema, REST APIs, databases, and distributed systems
• Knowledge of observability, automated testing, and version control
• Understanding of cloud computing
• Knowledge of DevOps and MLOps is a plus
• Experience in sectors such as Finance, Legal, Healthcare, Customer Service, or Technology is a plus
• Participation in AI projects deployed to production is a plus
• Experience with human evaluation and test dataset creation is a plus
• Knowledge of fine-tuning, LoRA, and supervised training is a plus
• Experience with LLM observability and evaluation platforms is a plus
• Knowledge of AI application security is a plus
• Advanced technical English is a plus
• Proven track record of reducing costs, improving accuracy, or delivering measurable automation is a plus

Core Competencies

Demonstrates advanced expertise in LLMs and multimodal models, with strong command of prompt engineering techniques and experience in integrating AI models with APIs and databases. Proficient in designing conversational flows and evaluating model performance while adhering to AI governance practices.

Highest-signal resume keywords

• Advanced Experience With LLMs
• Strong Command Of Prompt Engineering Techniques
• Knowledge Of Python
• Experience With AI Model APIs
• Understanding Of Machine Learning

ATS Optimization Keywords

Hard Skills

• Prompt Engineering
• Model Evaluation
• Natural Language Processing
• JSON Schema
• REST APIs
• RAG
• Embeddings
• Vector Databases
• Automated Testing
• Version Control

Soft Skills

• Mentoring
• Communication

Industry Keywords

• Finance
• Legal
• Healthcare
• Customer Service
• Technology

Tools & Technologies

• AI Models
• APIs
• Databases
• Distributed Systems
• Cloud Computing