Published: July 6, 2026

AI Engineer

Experience: 6 – 10 years

Position Summary

As an AI Engineer, you will build the data- and LLM-powered systems that turn AIQ’s models into production capabilities. Coming from a strong data-engineering foundation, you will design robust data pipelines and platforms and then apply that same rigour to large language models (LLMs) and agentic systems designing, building, and operating retrieval-augmented and multi-agent applications that integrate with enterprise data and services.

Responsibilities

• Design, build, and operate scalable data pipelines and platforms (batch and streaming) that feed AI and LLM applications.
• Develop LLM-powered and agentic systems — _tool calling, multi-agent orchestration, and autonomous workflows — _from prototype to production.
• Implement retrieval-augmented generation (RAG) using vector databases (Qdrant, Milvus, FAISS) and knowledge graphs.
• Engineer data ingestion, transformation, modelling, and quality (ETL / ELT) to support model training, evaluation, and inference.
• Build event-driven architectures and AI-workflow orchestration for reliable, observable pipelines.
• Deploy and optimise model serving and inference (latency, cost, throughput), and apply prompt-engineering and evaluation frameworks.
• Expose AI capabilities via REST APIs and microservices, and integrate them with enterprise applications and data platforms.
• Implement monitoring, evaluation, guardrails, and observability for LLM / agent systems (quality, safety, drift, cost).
• Collaborate with data scientists, ML engineers, backend, and product teams to deliver end-to-end solutions.

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Data Engineering, Machine Learning, or a related field.
• 6 – 10 years of experience, with a strong foundation in data engineering followed by hands-on LLM / agentic-system development.
• Proven data-engineering skills: building data pipelines and platforms, ETL / ELT, data modelling, and SQL / NoSQL stores.
• Hands-on experience building agentic AI systems (LLMs, agents, tool calling, multi-agent orchestration).
• Experience with RAG, knowledge graphs, and vector databases (e.g. Qdrant, Milvus, FAISS).
• Strong Python (e.g. FastAPI), with experience in microservices, REST APIs, and distributed systems.
• Experience deploying and optimising AI / ML models and inference in production.

Preferred Qualifications

• Experience with big-data and streaming tooling (Spark, Kafka, Airflow) and lakehouse / warehouse platforms (e.g. Databricks, Snowflake, BigQuery).
• Familiarity with LLM frameworks and orchestration (LangChain, LlamaIndex, LangGraph, or similar).
• Experience with cloud platforms (AWS, Azure, GCP) and containerisation / orchestration (Docker, Kubernetes).
• LLM evaluation, guardrails, and observability tooling.
• Exposure to MLOps / LLMOps practices and CI/CD for AI systems.