AI/ML Lead Engineer
Franklin Templeton22 days ago
Stamford, CT, USA or San Mateo, CA, USAStaff+
Base Salary
$180k - $212k/yr
Responsibilities
- Design and implement production-grade multi-agent systems and workflows using retrieval, reasoning, tool execution, validation, and compliance checks.
- Build distributed agent-execution services with observability, monitoring, failure handling, and high availability.
- Develop tools, data agents, and services that ground AI models in accurate data and knowledge.
- Embed AI agents and chatbots into client-facing platforms to generate portfolio insights for financial advisors.
- Create evaluation frameworks for reasoning accuracy, groundedness, hallucination mitigation, and financial correctness.
- Implement memory management, context handling, and agent-state persistence strategies.
- Refine knowledge bases and agent configurations based on interaction issues.
- Partner with product, design, and engineering teams to translate business requirements into robust agent architecture.
- Optimize production systems for latency, cost efficiency, and reliability.
- Contribute to decisions involving model serving, vector databases, caching, and orchestration layers.
- Architect scalable AI-agent infrastructure for workflow automation, dynamic tool invocation, structured output validation, observability, fault tolerance, and automated evaluation.
Requirements
- At least 5 years of software engineering experience, including at least 2 years building and deploying LLM, GenAI, or agent-based systems in production.
- Experience implementing multi-step agent workflows with LangChain, OpenAI function/tool calling, or similar orchestration frameworks.
- Expert-level proficiency in Python and experience building distributed services or microservices architectures.
- Hands-on experience with vector databases such as Pinecone or FAISS, RAG architectures, and data-grounding techniques.
- Experience implementing observability, monitoring, and fault-tolerant systems for high-availability applications.
- Preferred experience in asset management, wealth management, or portfolio analytics technology.
- Preferred experience designing LLM evaluation frameworks, model governance processes, hallucination mitigation, groundedness testing, accuracy testing, or compliance monitoring.
- Preferred experience designing or deploying multi-agent architectures with memory, state management, and orchestration layers.
- Preferred experience with model-serving frameworks, Docker, Kubernetes, and cloud platforms such as AWS, Azure, or GCP.
- A Master's or PhD in Computer Science, Machine Learning, AI, or a related discipline is preferred.
Benefits
- Hybrid schedule requiring work from the Stamford, San Ramon, or San Mateo office three days per week.
- Annual discretionary bonus and a 401(k) plan with a generous match.
- Healthcare, insurance, disability benefits, employee stock investment program, paid time off, and parental, caregiving, bereavement, and volunteering leave.
- Learning resources, career development programs, education-expense reimbursement, recognition rewards, and a wellbeing program.
Categories