Senior Generative AI Engineer

Key Responsibilities

• Build end-to-end Generative AI pipelines using Python, LangChain, and LangGraph.
• Design and implement agentic systems with tools, memory, branching, and recovery flows.
• Develop robust RAG systems (document ingestion, embeddings, vector search, hybrid retrieval).
• Integrate LLMs with APIs, SQL/NoSQL databases, and cloud storage.
• Build and maintain production-grade microservices/APIs for LLM workloads.
• Optimize AI systems for latency, throughput, and cost (prompting, caching, batching).
• Fine-tune models using LoRA/QLoRA and PEFT techniques.
• Implement evaluation, monitoring, guardrails, and hallucination detection.
• Collaborate with cross-functional teams to translate workflows into AI-powered features.
• Mentor junior engineers and contribute to AI architecture and code quality.

Core Requirements

• 4+ years of experience as an AI Engineer.
• Expert-level Python and strong ML/NLP fundamentals.
• Hands-on experience with Transformers, embeddings, and model evaluation.
• Strong experience with LangChain and LangGraph for building LLM workflows.
• Production experience with OpenAI APIs and prompt engineering.
• Deep understanding of RAG systems and vector databases (Qdrant or similar).
• Experience with fine-tuning (LoRA/QLoRA), PEFT, and dataset preparation.
• Practical experience with AWS, Docker, CI/CD, and deploying GPU workloads.
• Familiarity with PyTorch (preferred) or TensorFlow.
• Experience integrating external/internal data sources and building scalable AI microservices.
• Strong communication, problem-solving skills, and ability to work in fast-paced environments.