AI Engineer

Aiengis a high-growth innovative startup focused on delivering next-generation engineering solutions. We bridge the gap between ambitious vision and technical reality by investing heavily in research, development, and top-tier talent. Currently in a dynamic phase of expansion, we pride ourselves on our agility and our ability to navigate complex industrial challenges. At Aieng, we don’t just follow industry trends—we aim to set them. Join us as we build the infrastructure of tomorrow.As an AI Engineer (Inference & RAG Architect), you will design, optimize, and operate local, production-grade LLM systems, owning the full lifecycle from low-level inference performance to high-level semantic memory and agent orchestration.Architect and optimize high-throughput LLM inference pipelinesDesign and implement enterprise-grade RAG systemsBenchmark, validate, and fine-tune open-source models for domain-specific workloadsBuild agentic AI systems with deterministic, auditable behaviorEnsure scalability, observability, and reliability of AI systems in productionLLM Inference & Systems OptimizationAdvanced configuration and tuning of vLLM, Ollama, and TGIDeep understanding of PagedAttention, continuous batching, and KV-cache optimizationGPU scheduling, VRAM optimization, multi-GPU and multi-node inferenceCUDA-aware performance tuning (conceptual and practical)Deployment of LLMs in on-prem, edge, and air-gapped environmentsRetrieval-Augmented Generation (RAG) & Knowledge SystemsDesign of multi-stage RAG pipelinesIntegration with vector databases (Qdrant, Weaviate, FAISS)Hybrid retrieval strategies (dense, sparse, BM25)Re-ranking using cross-encoders and LLM-based rankersMetadata-driven access control and document-level securityChunking, embedding strategy design, and context window optimizationModel Lifecycle & EvaluationEvaluation and benchmarking of models such as Llama 3, Mistral, Phi, MixtralDomain adaptation via LoRA / QLoRAPrompt and system prompt engineering with reproducibility guaranteesOffline and online evaluation frameworks (faithfulness, groundedness, latency, cost)Versioning and rollback strategies for models and promptsAgentic Architectures & OrchestrationDesign of agent-based systems with tool use, memory, and planningDevelopment using Semantic Kernel, LangGraph, or custom agent frameworksDeterministic execution, guardrails, and fallback strategiesImplementation in Python and C#MLOps, DevOps & ObservabilityContainerization with Docker and orchestration via KubernetesCI/CD for AI systemsMonitoring of latency, throughput, hallucination rates, and failuresLogging, tracing, and observability for LLM pipelinesInfrastructure-as-Code (Terraform or equivalent)Strong system-level thinking and architectural mindsetObsession for performance, reliability, and correctnessAbility to translate business requirements into technical architecturesClear communicator in cross-functional, high-complexity environmentsOwnership mentality and engineering rigor3+ years of experience in AI Engineering, ML Systems, or Platform EngineeringStrong academic background in Computer Science, Engineering, or related fieldsProven experience deploying self-hosted LLMs in productionExposure to enterprise constraints (security, compliance, scalability)#J-18808-Ljbffr