Senior Software/AI engineer Central Europe

Zoolatech; Central (LA); On-site; USD 140,000 - 190,000; Full time

Job summary

Zoolatech is seeking a Senior AI Engineer to design, deliver, and scale production-grade AI solutions across enterprise workflows. You will architect agentic workflows, retrieval-augmented pipelines, and LLM-integrated applications that enable automation at scale.

You will work across full stack with a solid Python background, cloud experience, and hands-on AI/ML delivery, leading technical workstreams and mentoring engineers to translate business needs into concrete engineering solutions.

Qualifications

• 3–7+ years of hands-on experience in software, AI, or ML engineering and shipping production-grade systems.
• Advanced Python skills including concurrency, async patterns, and performance-aware design.
• Experience with Large Language Models (LLMs), including cost trade-offs and production behaviors.
• Experience enforcing structured LLM outputs and building reliable pipelines with LangChain or LangGraph.
• Strong ability to translate complex AI concepts for both technical and non-technical stakeholders.

Responsibilities

• Designing AI architectures and workflows before implementation, including triggers, processes, and system interactions.
• Building AI-driven solutions such as automated workflows, AI agents, and LLM-based applications.
• Implementing AI pipelines and integrations using LLM APIs, Python logic, and orchestration platforms.
• Developing systems that combine data sources and automate business processes.
• Identifying risks including security concerns, failure scenarios, and human-in-the-loop review.
• Continuously improving AI workflows by selecting appropriate technologies and approaches.
• Delivering solutions incrementally in phases for quick business adoption.

Skills

Python

LLMs

LangChain

LangGraph

Distributed systems

Docker

Kubernetes

Cloud platforms

Async patterns

Prompt engineering

Team leadership

Tools

Docker

Kubernetes

CI/CD

Job description

Our client is a global cybersecurity company focused on protecting millions of users and organizations through advanced digital security, privacy, and identity solutions. Their products help safeguard personal data, devices, and online interactions across a rapidly evolving digital landscape.

We’re hiring an experienced Senior AI engineer to join a growing AI engineering practice. In this role, you will design, deliver, and scale intelligent systems that drive real business outcomes. You will architect production-grade AI solutions spanning agentic workflows, retrieval-augmented pipelines, and LLM-integrated applications that enable enterprise automation at scale.

This role requires both deep technical expertise and strong delivery ownership, working across the full stack to take AI initiatives from whiteboard to production with speed and precision.

The team works on designing, building, and delivering enterprise AI solutions used by multiple departments across the company.

Key tasks include:

• Designing AI architectures and workflows before implementation, including defining trigger points, process flows, and system interactions
• Building AI-driven solutions such as automated workflows, AI agents, and LLM-based applications
• Implementing AI pipelines and integrations using tools such as LLM APIs, Python-based logic, and orchestration platforms
• Developing systems that combine different data sources (e.g., files, databases, or enterprise systems) and automate business processes
• Identifying potential risks such as security concerns, failure scenarios, and the need for human-in-the-loop review
• Continuously improving AI workflows by selecting the most appropriate technologies and development approaches
• Delivering solutions incrementally in smaller phases so business teams can start using them quickly and provide feedback

Solid full-stack or backend development background with advanced Python skills, including concurrency, async patterns, and performance-aware design

Familiarity with cloud platforms (AWS, Azure, GCP) and modern DevOps tooling including Docker, Kubernetes, and CI/CD pipelines

3-7+ years of hands-on experience in software, AI, or ML engineering with a track record of shipping production-grade systems

Practical experience working with Large Language Models (LLMs), including navigating API cost trade-offs and managing unpredictable model behaviours in production

Experience enforcing structured LLM outputs and building reliable pipelines using orchestration frameworks such as LangChain or LangGraph

Clear, confident communicator able to translate complex AI concepts for both technical peers and non-technical stakeholders

Strong grasp of Generative AI fundamentals and how they differ from conventional software development, particularly when solving open-ended or creative problems

Proficiency in prompt engineering techniques including multi-shot prompting, persona and tone setting, and structuring effective context and constraint

Proven ability to lead technical workstreams, mentor junior engineers, and translate ambiguous business needs into well-scoped engineering solutions

Nice to have

• Demonstrated ability to optimize AI workflows through systematic benchmarking, bottleneck analysis, and decomposing complex LLM call chains into efficient, maintainable components
• Practical judgment on when agentic architectures are appropriate including an honest assessment of their complexity, failure modes, and operational overhead
• Expertise in Retrieval-Augmented Generation (RAG): grounding model responses in authoritative knowledge bases and surfacing cited, verifiable claims
• Skilled in implementing input/output guardrails to defend against prompt injection, hallucinations, and harmful or policy-violating content

Explore similar open positions that match your experience.