LLM Engineer (AI)

The innovation division of a global digital intelligence and forensics corporation that develops investigative software solutions for law enforcement and government agencies worldwide.

The specialized innovation unit focuses on researching and deploying advanced AI capabilities, operating with dedicated resources and technological flexibility to integrate new systems into the company's core product portfolio.

The company is located in the Center region (train-accessible) and operates on a hybrid model of two days office-based.

Responsibilities-

• Developing and hardening core backend systems for generative AI platforms using Python.
• Integrating local LLMs, building RAG pipelines, and implementing agentic workflows.
• Managing production deployments in offline Linux environments using open-source utilities.
• Packaging services via Docker and optimizing container configurations for Kubernetes and edge devices.
• Implementing system observability, reliability protocols, and inference optimizations using quantization and caching.

Requirements

• 6 years of experience in software engineering.
• Strong proficiency in backend development using Python.
• Practical experience implementing AI workflows, specifically with LLM integration, RAG pipelines, Agentic flows, LangChain, or LangGraph (Mandatory).
• Hands-on experience with deployment systems, including Linux, Docker, or CI/CD pipelines (Mandatory).
• Experience with local vector databases such as Qdrant, Milvus, or pgvector (Advantage).
• Familiarity with cloud platforms, preferably GCP, or building robust web APIs (Advantage).
• B.Sc. in Computer Science or related fields, or background from a military technological unit (Advantage).