AI Engineer

Job Title: Generative AI Engineer (GenAI Engineer)Location: Remote / Hybrid (Flexible)

Department: AI/ML Engineering Employment Type: Full-time

Job DescriptionWe are looking for a talented Generative AI Engineer to design, build, and optimize production-grade generative AI applications.

You will work on end-to-end AI solutions that combine large language models (LLMs), retrieval-augmented generation (RAG), agentic workflows, and multimodal capabilities to deliver intelligent, scalable, and reliable AI products.You will be a key member of a high-performing team building next-generation AI systems using modern frameworks and tools.

Key ResponsibilitiesDesign, develop, and maintain production-ready GenAI applications using LangChain, LangGraph, and related orchestration frameworks.Build advanced RAG pipelines (including multi-stage retrieval, reranking, query transformation, and evaluation).Implement and optimize agentic workflows with LangGraph (stateful multi-agent systems, tool-calling, memory, human-in-the-loop).Work with vector databases (primarily Qdrant, also Pinecone, Weaviate, or Chroma) for efficient semantic search and retrieval.Fine-tune, quantize, and deploy LLMs and embedding models using PyTorch, Hugging Face Transformers, and PEFT methods (LoRA, QLoRA).Integrate and evaluate open-source and proprietary models (Llama 3, Mistral, Mixtral, GPT, Claude, Gemini, etc.).Implement evaluation frameworks (RAGAS, ARES, DeepEval, LangSmith) and monitoring for LLM applications.Optimize for cost, latency, and accuracy in production environments.Collaborate with backend, frontend, and data teams to integrate AI capabilities into user-facing products.Stay up-to-date with the latest advancements in LLMOps, agentic AI, and generative technologies.Technical Requirements (Must-Have)Strong proficiency in Python (advanced scripting, OOP, async programming, typing).Deep experience with LangChain & LangGraph (at least 1+ year of hands-on production use).Solid RAG expertise: advanced retrieval strategies, chunking, metadata filtering, hybrid search, reranking, and evaluation.Hands-on experience with Qdrant (or equivalent vector DBs) — collection management, filtering, hybrid search, payload optimization.PyTorch experience: model fine-tuning, LoRA/QLoRA, inference optimization (bitsandbytes, vLLM, TorchServe), custom training loops.Experience deploying LLMs (vLLM, TGI, Ollama, or cloud services like AWS Bedrock, Azure OpenAI, Vertex AI).Strong understanding of LLMOps (LangSmith, Phoenix, Helicone, Prometheus + Grafana).Experience with modern MLOps tools (Docker, Kubernetes, CI/CD, GitHub Actions).

Bachelor’s or Master’s degree in Computer Science, AI, Machine Learning, or equivalent experience.3+ years of hands-on experience building production GenAI / LLM applications.Proven track record of deploying scalable RAG and agent systems.Strong software engineering fundamentals (clean code, testing, design patterns, API development — FastAPI preferred).Published projects, GitHub repositories, or contributions to open-source LangChain/LangGraph ecosystem.