Senior AI Engineer (LLM)

Netcad started its journey in 1989 as the first company leading the digital transformation in Turkey. More than 30 engineering solutions offered by Netcad, have become the industry standard throughout Turkey in cadaster and cartography, urban planning, and infrastructure fields. With its experienced engineers and competent management staff, Netcad offers solutions with high efficiency, suitable for the smart data management needs of today's business world. Thanks to its expert R&D team, it closely follows technological trends and provides customer satisfaction-oriented service with innovative solutions for the needs of the business world that are increasing and diversifying every day. Working in cooperation with of its sector, Netcad creates added value for the country and offers the most suitable solutions for needs.

We're looking for a talented and experienced Senior AI Engineer to join our team!

Role Overview: We are seeking a Senior AI Engineer with a focus on Large Language Models (LLMs) for the development, evaluation, and production deployment of our generative AI capabilities. The ideal candidate has hands-on experience building LLM-powered applications (RAG, agents, copilots), optimizing them for reliability and cost and integrating outputs into real-world products and workflows. A key responsibility will be ensuring seamless integration of LLM results into our existing systems (APIs, databases, search and analytics) with attention to quality, safety and observability.

Key Responsibilities:

• Design, develop and deploy LLM-powered features (RAG, tool-using agents, chat assistants, structured extraction, summarization, classification),
• Build and improve retrieval pipelines (embedding, indexing, hybrid search, reranking) to maximize factuality and relevance,
• Develop evaluation frameworks for LLM (offline benchmarks, golden datasets, LLM-as-judge),
• Optimize inference performance and cost through prompt engineering, caching, batching, model selection, routing and fine-tuning where relevant,
• Implement guardrails and safety controls (policy filtering, prompt-injection resistance, PII handling, groundedness checks, citation strategies),
• Conduct research and prototyping on state-of-the-art methods (agentic workflows, long-context strategies, reranking, structured generation, fine-tuning),
• Create and maintain automated pipelines for data curation, prompt/version management, evaluation and continuous improvement.

Qualifications:

• Bachelor’s, Master’s, or Ph.D. in Computer Science, Electrical Engineering, or a related field,
• 4+ years of professional experience in ML/AI engineering or applied NLP (with production LLM experience strongly preferred),
• Proficiency in C# or Python with experience on building production services,
• Solid understanding of Transformer architectures, instruction tuning concepts, embeddings, and modern LLM application patterns (RAG, agents, tool calling),
• Proven ability to deploy and operate AI services in production, including monitoring, tracing, and incident response,
• Strong problem-solving and communication skills with the ability to work effectively in a collaborative environment.

Preferred Qualifications:

• Experience with fine-tuning (SFT/LoRA), distillation, or preference optimization,
• Background in building web-based AI products and internal developer platforms,
• Experience with security-minded LLM engineering (prompt injection testing, sandboxed tool execution, data leakage prevention),
• Publications or open-source contributions in NLP/ML or applied AI systems.

Nice-to-Have Tech Stack

PyTorch, Hugging Face, LangChain/LlamaIndex, vector search (FAISS/pgvector/OpenSearch), Docker/Kubernetes, Cloud (AWS/Azure/GCP)

We offer a competitive salary and benefits package, and the opportunity to work on challenging and impactful projects. If you're a passionate and skilled software engineer who thrives in a collaborative environment, we encourage you to apply!