Hire Resolve – Top Recruitment Agency
Ticking All Your Recruitment Needs
Ticking All Your Recruitment Needs
A leading internet provider is looking for a Senior AI Engineer to join their team in Middelburg, Mpumalanga.
The Mission:
We are building a sovereign, company-wide AI fabric. This system ingests every document, ticket, transaction, and data point across our portfolio (Veralogix, Bioniq, Innovata, Treadstone, Aiguille) into a unified retrieval, property-graph, and agentic layer. It provides natural-language, grounded, and traceable insights in real-time.
You will own the end-to-end architecture as part of a small, high-impact engineering team, focusing on on-prem-first deployment and seamless integration with our spatio-temporal platform.
Responsibilities:
Design and implement a chunking strategy for heterogeneous content: PDFs, scanned docs, transcripts, tables, code, and ERP records.
Engineer hybrid search (BM25 + dense + late-interaction), reranking, and query routing.
Architect and operate the vector database infrastructure (pgvector + Qdrant or equivalent).
Design and implement the ontology for the corporate knowledge graph (Memgraph, Neo4j, or KuzuDB).
Execute entity resolution across systems like Odoo, Aleph, Hoover, Elasticsearch, Nextcloud, and telemetry.
Build GraphRAG patterns that solve complex, multi-hop queries more effectively than naïve vector retrieval.
Author and manage a fleet of MCP servers to expose internal systems (Odoo, Hoover, Aleph, Memgraph, Elasticsearch, etc.) to the agent layer.
Implement robust scoping, authentication, auditing, and rate limiting.
Build and deploy multi-agent systems using frameworks like LangGraph, Pydantic AI, DSPy, or BAML.
Implement planner/researcher/executor/verifier patterns with structured outputs, error recovery, and long-running stateful workflows (e.g., using Temporal).
Build an evaluation harness from scratch with golden sets and RAGAS-style metrics.
Establish a rigorous “LLM-as-judge” methodology to block deploys on regression.
Set up observability (Langfuse/Phoenix), cost/latency dashboards, and a version-controlled prompt management system.
Requirements:
Production ML/AI: 5+ years of experience, with ≥2 years specifically on LLM-era systems (RAG, agents, fine-tuning).
Production RAG: Designed and operated a system over heterogeneous content. Can defend decisions on chunking, hybrid retrieval, and reranking from first principles.
Vector Databases: Deep operational knowledge of pgvector, Qdrant, Weaviate, or LanceDB. Has opinions on HNSW vs. IVF, quantization, hybrid indices, and index rebuild strategies.
Property Graphs: Production experience with Memgraph, Neo4j, or KuzuDB. Fluent in Cypher, has designed an ontology, and built production GraphRAG retrievers.
Agentic Tooling: Authored MCP servers or has equivalent depth with production tool-use design (OpenAI function calling, Bedrock agents).
Agentic Frameworks: Production experience with LangGraph, Pydantic AI, DSPy, or BAML. Has shipped multi-agent systems with real tool calls and recovery logic.
Evaluation Discipline: Has built an eval harness from scratch and can defend the metrics and regression rates of their prompt changes.
Information Extraction: Proficient with NER/RE models and structured-output pipelines (Pydantic/JSON schema/BAML) beyond simple prompting.
Python Mastery: Operating at a staff-engineer level. Can read research papers and implement them.
Model Fine-Tuning: Experience with LoRA/QLoRA or full fine-tuning of open-weight models.
Advanced Retrieval: Production experience with ColBERT, SPLADE, or similar late-interaction/ sparse-dense hybrid systems.
Novel RAG Architectures: Shipped systems like GraphRAG (Microsoft), Contextual Retrieval (Anthropic), or HippoRAG.
Entity Resolution at Scale: Experience with Splink, Zingg, dedupe, or similar libraries.
Local Model Serving: Skilled with vLLM, TensorRT-LLM, SGLang, or llama.cpp.
Spatio-Temporal RAG: Experience with natural-language querying over PostGIS + TimescaleDB.
OSINT Workflows: Integrated with tools like Maltego, SpiderFoot, Aleph, or Hoover.
Agentic Coding: Regular user of Claude Code or similar tools as a default working mode.
Open Source: Contributions to BAML, DSPy, LangGraph, or comparable libraries.
We will contact you telephonically in 3 days should you be suitable for this vacancy. If you are not suitable, we will put your CV on file and contact you regarding any future vacancies that arise.
