AI Engineer

This is a fully remote position, open to applicants in Philippines.

📋 Description

• Developing production-ready RAG pipelines

• Indexing and retrieving information from both unstructured files (such as Word, PDF, email, etc.) and structured relational database entries

• Knowledge of indexing methods including OCR (multi-modal), Element Extraction (Text, Table, Charts, etc.), Summary Generation, HyQE, Keyword Extraction, Embeddings (Dense, Sparse, Late-Interaction), and Named Entity Recognition

• Familiarity with advanced retrieval methods like Multi-Stage Retrieval, Content-Security-Policy, Filter Extraction, Query Rewriting, HyDE/HyQE, Query Expansion, Hybrid Search, and Reranking (bi- and cross-encoder)

• In-depth understanding of modern LLM-based systems beyond basic API usage

• Awareness of hyperparameters and model controls, including Temperature, Top-P, reasoning effort, structured output, etc.

• Strong skills in prompt engineering, involving instruction design, prompt structuring (e.g., XML tags / Markdown), sequencing of instructions, and differentiation between system/user prompts

• Experience in prompt versioning, variants, testing, and iteration using tools such as Agenta or similar

• Familiarity with common evaluation and retrieval quality metrics like Recall, Accuracy, F1, MRR, etc.

• Utilization of observability/tracing tools such as Langfuse via OpenTelemetry (OTEL) or similar technology stacks

• Profound understanding of tool invocation and the ability to design, scope, and segment tools to enhance reliability, maintainability, and overall system value

• Capability to design systems that do not merely expose “everything to the model,” but prioritize, preselect, and narrow down context (e.g., streamlining a large toolset to only the most pertinent candidates for specific tasks)

• Comprehension of concepts such as memory, state management, context persistence, and workflow continuity, including when and how to integrate these into agentic systems

• Familiarity with agentic architectures and the ability to decompose complex tasks into smaller, independently executable subtasks

• Insight into when workflows should be fully automated versus when Human-in-the-Loop (HITL) methods are necessary, and the ability to design such processes based on business logic, risk, and practical limitations

⛳️ Requirements

• At least 3 years of experience as an AI Engineer

• Practical experience with C#/.NET (1–2 years)

• Proven experience in creating production-ready RAG pipelines

• Strong grasp of Generative AI systems and their underlying model behaviors

• Experience in prompt management, evaluation, and observability

• Familiarity with agentic workflows and tool invocation

• Experience with C# Semantic Kernel and Semantic Memory as key AI infrastructure components, along with supporting technologies like RabbitMQ, MinIO, and Qdrant within a broader system architecture, or experience with similar AI orchestration stacks such as LangChain/LangGraph

• Background in working with self-hosted/open-weight LLMs

• Experience with inference infrastructure and deployment (vLLM, Linux-based environments, Dockerized applications)

• Experience with Multi-Modal AI (OCR, Audio)

• High level of autonomy and ownership

• Inquisitive and knowledgeable about the latest advancements in the field

• Excellent communication skills in English, with the ability to engage with international counterparts

🏝️ Benefits

• Opportunities for professional growth and development

• Collaborative and innovative work environment

• Flexible working arrangements

• Competitive salary and benefits package