Key skills
Generative AIMulti-Agent SystemsPythonDistributed SystemsCloud InfrastructureLLM ApplicationsSystems ThinkingResilienceAdaptabilityAIMLLLMAWSAzureGCPCaching
About this role
TIFIN builds AI-powered financial technology that personalizes and improves financial advice across various sectors. They are seeking a Staff AI Engineer to architect, build, and operationalize production-grade multi-agent systems that enhance advisor capabilities and automate workflows.
Responsibilities:
- Design and implement production-grade multi-agent systems using modern agent frameworks (e.g., Pydantic AI, Agent Harness, Tool-Calling, Code Execution)
- Build agent workflows that integrate context retrieval, reasoning, tool execution, validation, and compliance checks
- Develop distributed services for agent execution with strong observability, monitoring, and failure handling
- Establish evaluation frameworks for multi-step reasoning accuracy, groundedness, hallucination mitigation, and financial correctness
- Implement memory management, context handling, and agent state persistence strategies
- Partner with product, design, and engineering teams to translate business requirements into robust agent architectures
- Optimize systems for latency, cost efficiency, and reliability in production
- Contribute to infrastructure decisions around model serving, vector databases, caching, and orchestration layers
Requirements:
- 3+ years of experience building and shipping Generative AI and LLM applications into production, 6+ years of ML experience
- Demonstrated experience designing and deploying multi-agent systems of various architecture
- Strong experience with multimodal LLMs, knowledge graph, data synthesis, LLM fine tuning, reinforcement learning, agent harness, agent memory
- Deep proficiency in Python and modern AI frameworks
- Experience with distributed systems, cloud infrastructure (AWS/GCP/Azure), and containerized deployments
- Experience implementing monitoring, evaluation, and reliability safeguards for AI systems
- Strong systems thinking — ability to design beyond single-model solutions toward coordinated, multi-component architectures
- Resilience and adaptability - experience working at early-stage startups is a plus