ML Developer Sr – Data Agents

Dayforce

20h

About The Position

We are looking for a Senior Software Developer to join the team building AI Agent capabilities in Dayforce, with a focus on data-centric agents. This role is ideal for someone who can design, build, and ship production-quality agent systems—including a natural language to SQL (NL2SQL) solution—using modern agent frameworks (LangChain, LangGraph, Python) and AI development tools (Copilot, Claude, GitHub Copilot Agents, IDE agents, and internal agents). The goal is to accelerate delivery while maintaining high standards for quality, security, and operational excellence. This is a high-impact role. You will help transform how millions of users across 150+ countries interact with Dayforce by enabling natural language access to data and automating complex data workflows through intelligent agents. You will work across the full software lifecycle—architecture, design, prototyping, implementation, testing, release, and production operations—and partner closely with product, platform, and engineering teams.

Requirements

Strong Python development experience with a proven track record of building production systems
Hands-on experience building agents using LangChain, LangGraph, or comparable frameworks, including tool use and multi-step workflows
Experience building or contributing to NL2SQL or other natural-language-to-structured-query systems
Strong SQL expertise, including complex query authoring, optimization, and schema comprehension across large, normalized data models
Solid system fundamentals, including data structures, algorithms, design patterns, API design, and reliability engineering
Experience with microservices and API-based architectures
Experience with cloud platforms, with Azure strongly preferred
Experience testing and evaluating LLM-based systems for accuracy, safety, and hallucination mitigation
Familiarity with version control and CI/CD workflows using Git, GitHub, or Azure DevOps
Demonstrated use of AI tools to accelerate feature delivery while maintaining high-quality pull requests
Rapid prototyping and iteration supported by automated tests
Refactoring and modernization with strong automated safety nets
Effective use of AI for debugging, including log analysis, hypothesis generation, and targeted fixes
Proficiency in English is required for this position as this role will regularly interact with English-speaking stakeholders, co-workers, managers and/or clients across the world.

Nice To Haves

Experience with recursive language models (RLMs) and iterative inference strategies
Experience with sandboxed execution environments for safely running dynamic or generated code
Background in data engineering, including ETL/ELT pipelines, data modeling, and data warehousing
Experience with retrieval-augmented generation (RAG), vector databases, and embedding-based retrieval
Kubernetes experience, including deployments, scaling, and troubleshooting
Azure PaaS experience, such as Azure SQL, Functions, Key Vault, Storage, Azure Monitor, and Log Analytics
Kafka integrations across databases, microservices, or stream-processing systems
Strong observability and reliability practices, including monitoring, alerting, and SLOs
DevOps automation experience using tools such as Terraform, ARM templates, or PowerShell
Experience with prompt engineering, fine-tuning, and LLM evaluation frameworks

Responsibilities

Design, build, and maintain data-centric AI agents, including an NL2SQL solution that translates natural language queries into accurate and performant SQL against complex enterprise data models
Develop agent architectures using LangChain, LangGraph, and Python, including tool use, multi-step workflows, and structured reasoning patterns
Build robust evaluation, testing, and observability patterns to ensure correctness, reliability, and safety of agent outputs
Design and implement guardrails, validation layers, and sandboxed execution environments to safely run generated SQL and agent-produced code in production
Continuously improve agent accuracy and relevance through prompt engineering, fine-tuning strategies, and feedback loops
Design and implement new microservices, evolve existing services, and build or consume well-designed APIs to support agent and data workflows
Own critical areas of the agent codebase and provide technical stewardship for shared patterns and libraries
Improve performance, relevance, and reliability of data agent services through profiling, tuning, and iterative optimization
Build tooling and automation around releases, integrations, and operational workflows
Contribute to long-term improvements in production support, incident learnings, reliability, and operational maturity
Actively use AI tools to increase engineering throughput while maintaining correctness, maintainability, and security.
AI-assisted scaffolding with rigorous human review
AI-generated test suites and regression harnesses
Fast refactoring and modernization supported by automated verification
Agentic workflows for repetitive engineering tasks such as migrations, API clients, documentation, and runbooks
Secure and responsible AI usage with strong review discipline, no sensitive data leakage, and traceable change sets
Partner with product and engineering stakeholders to understand data access needs and translate them into agent-driven solutions
Translate business requirements into clear, well-reasoned technical designs
Present system designs and complex technical topics to both technical and non-technical audiences
Mentor peers through pairing, coaching, and high-quality code and design reviews
Take an organization-first approach to accountability, prioritizing business outcomes over individual ownership