SDE III Gen AI

Key details

Full job description

Design and implement production-ready generative AI applications serving millions of users. Build advanced RAG pipelines combining vector databases, hybrid search, and caching. Develop multimodal AI systems integrating text, vision, and audio. Architect scalable microservices optimizing cost, latency, and reliability. Lead code reviews and technical design sessions. Optimize large language models through fine-tuning. Implement MLOps practices including automated testing, model versioning, A/B testing, and monitoring. Collaborate with product managers to translate business requirements into AI solutions. Deploy AI models on GCP using containerization and orchestration. Maintain technical documentation and mentor junior engineers. Research and prototype emerging AI technologies. Fine-tune language models for business use cases. Design multi-agent AI systems and implement advanced prompt engineering. Build embedding systems handling billions of vectors. Develop computer vision pipelines. Create secure AI applications with safeguards and compliance. Optimize token usage and caching to reduce costs. Design evaluation frameworks with human feedback. Build real-time AI inference systems with sub-100ms latency. Integrate multiple foundation models with fallback and load balancing. Develop tools extending LLM capabilities. Implement advanced RAG techniques and multimodal search systems. Build AI-powered data pipelines and deploy edge AI solutions using ONNX and TensorRT. Requires 5+ years ML/AI experience, 2+ years in generative AI, expert Python skills, experience with PyTorch, Transformers, LangChain, vector DBs, GCP, Docker, Kubernetes, and strong communication skills. Bachelor's degree required; Master's preferred.