Senior AI & Software Engineer

Jobtailor; Deutschland; Vor Ort; EUR 90.000 - 130.000; Vollzeit

Zusammenfassung

Jobtailor is seeking an experienced software engineer to take ownership of core AI architecture components and build scalable AI agent systems. The role emphasizes reliability, evaluation, and observability to ensure high-quality AI outputs.

Collaboration with Business and Product teams will drive tangible business impact. The ideal candidate has 6–8+ years in software engineering, strong Python (Django) skills, and hands-on experience with LLM APIs and AI system design to shape long-term

Qualifikationen

• 6–8+ years of software engineering experience, ideally in AI/LLM environments.
• Very strong Python skills (Django or similar).
• Experience with LLM APIs (OpenAI, Claude, etc.) and AI system design.
• Knowledge of evaluation methodologies and observability.
• Understanding of reliability vs. speed/quality trade-offs in AI systems.

Aufgaben

• Take ownership of central components of the AI architecture.
• Design and develop scalable AI agent systems (multi-step reasoning, decision pipelines, tool use).
• Be responsible for the reliability and quality of AI outputs (evaluation, monitoring, guardrails).
• Advance LLM systems (prompting, fine-tuning, tooling, memory, orchestration).
• Build observability and evaluation frameworks (regression tests for AI).
• Work closely with Business and Product teams to drive real impact on processes and revenue.
• Make technical decisions with long-term impact (architecture, stack, scaling).

Kenntnisse

Python

Django

LLM APIs

AI system design

Evaluation methodologies

Observability

Reliability trade-offs

Jobbeschreibung

• Take ownership of central components of the AI architecture
• Design and develop scalable AI agent systems (multi-step reasoning, decision pipelines, tool use)
• Be responsible for the reliability and quality of AI outputs (evaluation, monitoring, guardrails)
• Advance LLM systems (prompting, fine-tuning, tooling, memory, orchestration)
• Build observability and evaluation frameworks (regression tests for AI)
• Work closely with Business and Product teams to drive real impact on processes and revenue
• Make technical decisions with long-term impact (architecture, stack, scaling)

Requirements

• 6–8+ years of experience in software engineering (ideally with AI/LLM environments)
• Very strong Python skills (Django or similar)
• Experience with: LLM APIs (OpenAI, Claude, etc.), AI system design
• Evaluation methodologies and observability
• Understanding of how to make AI systems reliable and the trade-offs between speed and quality

Core Competencies

Demonstrates expertise in designing and developing scalable AI systems, with a strong focus on reliability, evaluation methodologies, and observability frameworks. Proficient in Python and experienced in working with LLM APIs to drive impactful business outcomes.