AI Engineer - #35029

Job Description

As an AI Engineer, you will be responsible for building production-grade RAG pipelines across both structured and unstructured data. This role requires a deep understanding of LLM behavior, prompt engineering, and advanced retrieval techniques. You will also design and optimize agentic workflows, implement effective tool-calling strategies, and ensure system reliability through evaluation, observability, and continuous iteration.

You will also contribute to their AI platform, including an AI chat for legal professionals and orchestrating workflows, as well as context-aware AI features in Outlook and Word—such as intelligent email classification, attachment handling, and in-context document assistance (e.g., rewriting in redline mode).

Company Profile:

Our client is a Vienna-based IT company with over 50 employees across locations in Austria and Poland. The company is a key player in electronic filing and IT services, offering not only standard software and hardware solutions but also highly specialized industry applications. For more than two decades, its tailored solutions have earned the trust of a wide range of clients—including law firms, notaries, corporate legal departments, and public institutions—serving over 1,250 customers and 15,000 active users.

As a recognized innovator in legal tech, the company places a strong emphasis on developing industry-specific solutions, with a particular focus on the legal sector. Apart from that the company does not only provide established solutions in the sectors of surveying and real estate, but also offers general electronic filing, ERP systems, and scalable IT services tailored to businesses of all professions and all sizes.

Building on this foundation, the strategic direction is to further develop the Angular-based successor to its core legal product and to complement this new, constantly evolving product by developing related add-ons & integrations to support its core (e.g. office integration, automatic time tracker, AI integration & so on).

Due to their continued success, they are looking to building their team in the Philippines and are seeking a skilled AI Engineer to join their dynamic technical team.

This is an incredible career opportunity for someone who wants to gain experience in modern technologies, and tools. Career growth, state-of-the-art technologies to learn, and a highly collaborative working environment with brilliant people are some of the things that you could look forward to!

Duties and Responsibilities:

Building production-grade RAG pipelines

• Indexing and retrieving across both unstructured files (Word, PDF, email, etc.) and structured relational database entries
• Familiarity with indexing techniques such as OCR (multi-modal), Element-Extraction (Text, Table, Charts etc.), Summary Generation, HyQE, Keyword Extraction, Embeddings (Dense, Sparse, Late-Interaction), Named Entity Recognition etc.
• Familiarity with advanced retrieval techniques such as Multi-Stage Retrieval, Content-Security-Policy, Filter-Extraction, Query-Rewriting, HyDE/HyQE, Query-Expansion, Hybrid-Search and Reranking (bi- und crossencoder) etc.

Generative AI systems and underlying model behavior

• Deep understanding of how modern LLM-based systems work beyond simpleAPI usage
• Knowledge of hyperparameters and model controls such as Temperature, Top-P, reasoning effort, structured output, etc.
• Solid prompt engineering skills, including instruction design, prompt structuring (e.g. XML tags / Markdown), ordering of instructions, separation between system / user prompts etc.

Prompt management, evaluation, and observability

• Prompt versioning, variants, testing, and iteration using tools such as Agenta or similar
• Common evaluation and retrieval quality metrics such as Recall, Accuracy, F1, MRR, etc.
• Use of observability / tracing tools such as Langfuse via OpenTelemetry (OTEL) or comparable stacks

Agentic workflows and tool calling

• Understand tool calling in depth and know how to properly design, scope, and separate tools to maximize reliability, maintainability, and overall system value
• Design systems that do not simply expose “everything to the model”, but instead apply tool prioritization, preselection, and contextual narrowing (e.g. reducing a large toolset to only the most relevant candidates for a given task)
• Understand concepts such as memory, state handling, context persistence, and workflow continuity, and know when and how these should be incorporated into agentic systems
• Familiar with agentic architectures and know how to break down complex tasks into smaller, independently executable subtasks
• Understand when workflows should be fully automated versus when Human-in-the-Loop (HITL) patterns are required, and are able to design such processes based on business logic, risk, and practical constraints

Requirements

• Minimum of 3 years of experience as an AI Engineer
• Hands-on experience with C#/.NET (1–2 years)
• Experience building production-grade RAG pipelines
• Strong understanding of Generative AI systems and underlying model behavior
• Experience with prompt management, evaluation, and observability
• Familiarity with agentic workflows and tool calling
• Experience with C# Semantic Kernel and Semantic Memory as core AI infrastructure stack, complemented by supporting technologies such as RabbitMQ, MinIO, and Qdrant within the broader system architecture, or experience with comparable AI orchestration stacks like LangChain/LangGraph
• Experience working with self-hosted / open-weight LLMs
• Experience with inference infrastructure and deployment[NU2.1] (vLLM, Linux-based environments, Dockerized applications)
• Experience with Multi Modal AI (OCR, Audio)
• High degree of autonomy and ownership
• Curious and up to date with the latest developments
• Excellent communication skills in English, with the ability to communicate with foreign counterparts

Advantageous skills or nice-to-haves:

• Bachelor’s degree in Computer Science, Information Technology, or a related field
• Experience with GraphRAG
• Experience with model fine-tuning
• Domain experience in legal tech or similar knowledge-heavy domains