Senior AI/ML Engineer

Jobtailor; Kraków; On-site; PLN 180,000 - 260,000; Full time

Job summary

Jobtailor is seeking an experienced AI engineer in Kraków to own the AI engine, designing context architectures, templates, few-shot prompts, and structured outputs for production systems.

You will architect agentic workflows, define tool interfaces, manage state across turns, and ensure robustness with guardrails, observability, and cost-aware operations spanning the stack from Python backends to databases.

Qualifications

• 3+ years shipping AI/LLM features in production.
• Hands-on context architecture design: prompt engineering, structured outputs, schema validation.
• Experience operating agentic systems with tool interfaces and state management.
• Systematic approach to AI quality with eval sets and failure analysis.
• Production AI observability including tracing, cost monitoring and latency tracking.
• Proficiency in Python (production‑grade).
• Fluent English, written and spoken.

Responsibilities

• Own the AI engine with context architectures and schemas.
• Architect and ship agentic workflows with robust interfaces.
• Drive AI quality with evals and failure analysis.
• Oversee AI production operations including cost and SLOs.
• Write backend Python APIs, microservices, and databases.
• Promote clean code and testing pyramid across the team.

Skills

AI engineering experience

Context architecture design

Agentic systems experience

Python production code

Backend fundamentals

English fluency

Tools

Cursor

Claude Code

Copilot

Job description

Responsibilities

• Own the AI engine: Design and evolve context architectures (templates, few-shot examples, structured outputs); manage context window limits; optimize for quality and cost; validate schemas and handle edge cases.
• Architect and ship agentic workflows: Design agent boundaries, clean tool interfaces, failure handling, and human oversight points; manage agent state across turns; ensure robustness through guardrails and graceful degradation.
• Drive AI quality: Define success criteria before shipping; build and run eval sets; catch regressions before users do; analyze failure patterns systematically; iterate on evidence, not gut feel.
• Own AI production operations: Trace LLM calls and agent steps across the stack; monitor cost and latency; set SLOs; respond to incidents; establish operational runbooks.
• Write solid Python backend code: Build APIs, microservices, and database schemas that support the above; own deployment and on-call for your services.
• Raise the engineering bar: Champion clean code, the testing pyramid, and sharp code reviews across the team.

Requirements

• 3+ years shipping AI/LLM-powered features in production (not research, not prototypes)
• Hands‑on context architecture design: Prompt engineering, structured outputs, schema validation, few‑shot design, context window optimization
• Experience building and operating agentic systems: Tool interface design, orchestration patterns, failure handling, agent state management, multi‑turn conversations
• Systematic approach to AI quality: Eval sets, success criteria definition, failure pattern analysis, evidence‑based iteration
• Production AI observability: Tracing LLM calls and agent steps, cost monitoring, latency tracking, incident investigation
• Proficiency in Python (production‑grade, enterprise experience)
• Solid backend fundamentals: APIs, microservices, SQL database design and optimization
• Daily hands‑on use of AI development tools (Cursor, Claude Code, Copilot, or similar) — this is a hard requirement
• Fluent English (written and verbal)
• Self‑driven, product‑minded, no hand‑holding needed
• Has owned a non‑trivial AI feature or agentic workflow in production for 12+ months — context design, evals, on‑call, iteration on real user feedback