SDE III Gen AI

What you'll do

• Design and implement production-ready generative AI applications serving millions of users
• Build advanced RAG pipelines combining vector databases, hybrid search, and intelligent caching
• Develop multimodal AI systems integrating text, vision, and audio capabilities
• Architect scalable microservices handling thousands of concurrent AI requests optimizing cost, latency, reliability
• Lead code reviews and technical design sessions, establish best practices and architectural patterns
• Optimize large language models through fine-tuning for domain-specific performance
• Implement comprehensive MLOps practices including automated testing, model versioning, A/B testing, real-time monitoring
• Collaborate with product managers and stakeholders to translate business requirements into AI solutions
• Deploy AI models across multiple cloud platforms (GCP) using containerization and orchestration
• Create and maintain technical documentation, runbooks, architectural decision records
• Mentor junior engineers through pair programming, technical talks, and hands-on guidance
• Research and prototype emerging AI technologies for competitive advantage
• Fine-tune and optimize state-of-the-art language models for business use cases
• Design multi-agent AI systems using orchestration frameworks
• Implement advanced prompt engineering strategies
• Build production-grade embedding systems handling billions of vectors with efficient indexing and hybrid search
• Develop computer vision pipelines for object detection and visual question answering
• Create secure AI applications with safeguards against prompt injection, jailbreaking, data leakage, and ensure AI governance compliance
• Optimize token usage and implement intelligent caching to reduce costs by 50-70%
• Design and implement evaluation frameworks incorporating human feedback and domain-specific quality measures
• Build real-time AI inference systems processing streaming data with sub-100ms latency
• Integrate multiple foundation models with fallback mechanisms and load balancing for high availability
• Develop custom tools/functions extending LLM capabilities to interact with databases, APIs, external systems
• Implement advanced RAG techniques including contextual embeddings, cross-encoder reranking, Graph RAG
• Create multimodal search systems querying text, images, documents using natural language
• Build AI-powered data processing pipelines to extract, transform, enrich unstructured data at scale
• Deploy edge AI solutions using ONNX and TensorRT optimizing models for resource-constrained environments

Requirements

• 5+ years of hands-on experience building and deploying ML/AI systems
• At least 2+ years focused on generative AI and LLMs
• Expert-level Python programming skills with async programming, multiprocessing, and performance optimization
• Strong experience with modern AI frameworks including PyTorch, Transformers, LangChain, and vector databases
• Proven track record of deploying AI applications to production environments serving real users at scale
• Deep understanding of transformer architectures, attention mechanisms, and latest advances in generative AI
• Experience with cloud platforms (GCP) and containerization technologies (Docker, Kubernetes)
• Excellent communication skills to explain complex AI concepts to technical and non-technical audiences
• Proven experience improving large-scale product search and discovery including dense retrieval, cross-encoder reranking, query understanding, hybrid BM25 + vector search
• Hands-on experience building and deploying production multi-agent systems using orchestration frameworks such as LangGraph and Google ADK
• Bachelor's degree in Computer Science, Mathematics, or related field (Master's preferred but not required)

Tech stack

Benefits