AI Technical Lead, IANS Research

• 5+ years of experience in AI/ML engineering, with 2+ years in a senior or lead role
• Hands-on experience designing agentic AI systems, AI agents, or multi-agent frameworks for production environments
• Deep expertise with LLMs, NLP, RAG pipelines, embeddings, and generative AI technologies
• Strong Python engineering skills; experience with PyTorch, TensorFlow, Hugging Face, LangChain, etc
• Experience architecting APIs, SDKs, or developer-facing tools used by external customers
• Strong understanding of distributed systems, cloud infrastructure (Azure preferred), and scalable architectures
• Familiarity with MLOps workflows, CI/CD, model monitoring, evaluation, and lifecycle management
• Strong communication, leadership, and cross-functional collaboration skills

Desirable

• We are seeking a highly skilled AI Technical Lead to drive the design, development, and evolution of both our internal AI systems and our client-facing agent platforms
• This role serves as the technical authority across AI initiatives—architecting agentic systems, building reusable frameworks, and guiding the engineering strategy that powers IANS’ next generation of data-driven products
• You will own the full lifecycle of AI and ML systems, with deep expertise in LLMs, retrieval-augmented generation (RAG), agent design, and enterprise-grade architecture
• Lead the design and development of AI agent systems aligned with IANS’ evolving DaaS strategy, enabling clients to consume IANS data feeds and build their own AI agents using proprietary, internal, and third-party data
• Architect agentic workflows that orchestrate retrieval, reasoning, tool use, planning, and action execution across enterprise contexts
• Develop reusable agent frameworks, primitives, and SDK-style abstractions that external clients can safely and flexibly extend for their own applications
• Integrate RAG pipelines, tool use, APIs, and multi-agent patterns into robust, production-grade platforms
• Define scalable abstractions for agent memory, tool orchestration, context management, and autonomous task execution
• Shape the long-term AI and agent-platform roadmap in partnership with product and engineering leaders
• Serve as the primary subject-matter expert on agentic systems, LLM architectures, RAG, and DaaS platform design
• Provide technical leadership and mentorship across AI initiatives, ensuring consistent engineering excellence
• Evaluate emerging technologies, frameworks, and standards relevant to AI agents, data delivery, automation, and platform extensibility
• Develop production-grade Python code using frameworks such as PyTorch, TensorFlow, Hugging Face, LangChain, and modern agent toolkits
• Design and maintain APIs, microservices, and developer-facing interfaces that enable both internal and external teams to integrate with IANS’ data and agent platforms
• Implement robust testing, observability, logging, and performance optimization for complex agent workflows and model-driven systems
• Ensure compatibility between internal systems and externally consumed SDKs, tools, and data interfaces
• Architect and manage scalable cloud-based AI/agent infrastructure (Azure preferred)
• Implement MLOps pipelines for continuous delivery, safe model updates, monitoring, evaluation, and governance
• Build and maintain data pipelines supporting RAG, retrieval, embeddings, agent memory, and inference
• Establish observability frameworks for agent behavior, tool interactions, and cost management
• Define and enforce strict standards for security, data isolation, governance, observability, and cost control, especially when exposing agent capabilities and data products to clients
• Ensure safe sandboxing, permissioning, and policy enforcement for client-built AI agents
• Oversee compliance with regulatory frameworks (GDPR, CCPA, etc.) and responsible AI practices including fairness, explainability, privacy, and risk mitigation