AI/Agent Engineer (5 positions)

About the role

We are building the next generation of production AI agent systems that reason, plan, call tools, delegate across specialized sub‑agents and deliver real business outcomes end‑to‑end. The role requires deep expertise in modern machine learning, transformers and agents to ship robust, scalable solutions.

Key responsibilities

• Architect agentic systems – planning, memory, tool use, multi‑agent delegation, evaluation loops and guardrails.
• Push model capability into production – design prompt and context strategies, tool interfaces, retrieval, reranking, structured output, streaming and evaluation across text and multimodal inputs.
• Own the evaluation story – build offline eval sets, online LLM‑as‑judge loops and regression harnesses.
• Squeeze the system – implement prompt caching, batching, speculative decoding, model routing and token‑budget management to meet latency targets.
• Contribute upstream – read SDK source, open PRs to open‑source agent frameworks and write clear bug reports.
• Mentor and set the bar – lead design and code reviews, shaping the team’s approach to agents.

Required profile

• Bachelor’s degree in Artificial Intelligence, Computer Science or related field.
• 3+ years experience as an AI/Agent Engineer.
• Solid ML fundamentals with deep understanding of transformers, attention, KV cache and sampling.
• Production experience with frontier LLMs (Anthropic, OpenAI, Gemini, open‑weight) and agent‑behaviour systems.
• Hands‑on multimodal work (vision‑language, OCR, audio) from ingest to grounded output.
• Strong engineering craft in Python, async programming, typing, testing and observability.
• Production AI engineering skills – API design, RAG pipelines, containerisation, CPU/GPU deployment and performance optimisation.
• AI platform & MLOps experience – Docker, Kubernetes/AKS, Azure AI services, GPU inference, vLLM or NVIDIA Triton.

Required skills

• Python (async, typing, testing, packaging)
• Transformers, attention mechanisms, KV cache, tokenisation
• LLM APIs (Anthropic, OpenAI, Gemini, open‑weight)
• Agent frameworks, tool orchestration, multi‑agent delegation
• Vision‑language models, OCR, document AI, audio processing
• Docker, Kubernetes/AKS, Azure AI services, GPU inference
• vLLM, NVIDIA Triton, prompt engineering, retrieval‑augmented generation
• Vector search, evaluation pipelines, CI/CD for AI models

What we offer

• 13th‑month salary bonus and attractive performance bonus
• 100% monthly salary and mandatory social insurances after a 2‑month probation
• Meal, commuting and parking allowance
• Premium health insurance for employee and two family members
• 15+ days annual leave plus a birthday leave day
• Flexible working time, onsite entertainment facilities and sport activities