Senior AI/ML Engineer

We're seeking a Senior AI/ML Engineer with deep expertise in architecting and scaling agentic AI systems. You'll lead the design and implementation of sophisticated autonomous agents, establish best practices for AI system development, and mentor junior engineers. This role bridges advanced machine learning concepts with production engineering, creating robust, scalable agentic solutions for complex business problems. Key Responsibilities Architect end-to-end agentic AI systems including agent design, orchestration, and integration with enterprise systems Design advanced agent patterns including hierarchical agents, multi-agent collaboration, and dynamic tool management Lead the development of sophisticated reasoning architectures with planning, reflection, and self-correction mechanisms Establish and implement evaluation frameworks, bench-marking methodologies, and cost optimization strategies for agentic systems Build scalable prompt engineering pipelines and fine-tune LLMs for specific use cases and domains Design and implement RAG systems with advanced retrieval strategies, knowledge management, and semantic search Develop production-grade monitoring, observability, and error handling for AI systems at scale Mentor junior engineers on agentic AI patterns, best practices, and system design principles Lead technical design reviews and architectural decisions for AI/ML initiatives Collaborate with product, infrastructure, and security teams to ensure responsible AI deployment Drive innovation in agentic AI approaches and evaluate emerging frameworks and models Optimize system performance, latency, and costs across production agentic workflows Establish CI/CD and testing practices specific to AI/ML systems Requirements Required Skills: 5-7 years of professional software development or machine learning experience, with 2+ years focused on agentic AI Proven track record building production agentic AI systems with measurable business impact Expert-level proficiency in Python and software engineering best practices (design patterns, testing, documentation) Deep experience with multiple LLM providers and APIs (OpenAI, Anthropic Claude, Azure OpenAI, open-source models) Advanced knowledge of prompt engineering, prompt chaining, chain-of-thought reasoning, and few-shot learning Hands-on expertise with agentic frameworks (LangChain, CrewAI, Autogen, Semantic Kernel, or equivalent) Strong understanding of tool use, function calling, and dynamic agent capability management Experience architecting retrieval-augmented generation (RAG) systems with vector databases and semantic search Knowledge of model fine-tuning, domain adaptation, and custom model training Proficiency with asynchronous programming and handling high-concurrency systems Experience with API design and integration patterns for complex distributed systems Strong background in software testing, including evaluation frameworks for AI systems Preferred Qualifications Experience deploying and managing agentic systems in production at scale Cloud platform expertise (Azure, AWS, GCP) for AI/ML services and infrastructure Background building observability, monitoring, and debugging tools for ML systems Experience with multi-agent systems, agent communication protocols, and collaborative agent patterns Knowledge of reinforcement learning from human feedback (RLHF) or similar alignment techniques Familiarity with knowledge graphs, semantic databases, and advanced retrieval strategies Experience optimizing token usage and managing costs for LLM-based applications Background in enterprise software or complex system integration Experience with MLOps, model versioning, and continuous integration for AI systems Leadership or mentoring experience with junior engineers Nice to Have Published research, papers, or significant open-source contributions in AI/ML Experience with agent-as-a-service architectures or API platforms Background in building customer-facing AI products Knowledge of adversarial testing and robustness evaluation for AI systems Experience with specialized domains (financial services, healthcare, legal, etc.) Understanding of AI safety, alignment, and ethical considerations in agent design Experience building domain-specific large language models or specialized agent systems