‹ Back
Senior Machine Learning Engineer
JOB SUMMARY
Roles
Job details
We're looking for a Senior Machine Learning Engineer to join our AI team at ApprovalMax.
You'll design and build agentic AI systems that automate complex approval workflows for finance teams across 17,000+ businesses.
This is a high-impact role where your work directly shapes how companies handle millions of financial transactions.
What You'll DoDesign, build, and deploy agentic systems using LangGraph and LangChain for workflow automationDevelop and maintain ML models for anomaly detection, fraud prevention, and intelligent document processingBuild evaluation frameworks and implement observability using LangFuseDeploy and scale ML services using Ray Serve or FastAPI + Redis + CeleryWork with vector databases (pgvector) for RAG-based retrieval systemsCollaborate closely with product and engineering to ship AI features with high accuracy
requirements
Contribute to architectural decisions for our growing AI infrastructureWhat You BringRequired:4+ years of production ML experienceStrong Python skills with strict typing practicesHands-on experience building LLM-powered applications (agents, RAG, prompt engineering)Experience with at least one agent framework (LangGraph, LangChain, or similar)Solid foundation in classical ML (classification, regression, anomaly detection)Experience deploying ML models to production (Ray Serve, FastAPI, or equivalent)Familiarity with async processing patterns (Celery, Redis, or similar)Nice to Have:Experience with Azure cloud services (Azure OpenAI, Container Apps)Background in fintech or financial document processingExperience with ML observability tools (LangFuse, LangSmith, Weights Biases)Knowledge of vector databases and embedding modelsExperience with evaluation frameworks for LLM applicationsTech StackLanguages: PythonAgent Frameworks: LangGraph, LangChainDeployment: Ray Serve, FastAPI, Celery, RedisObservability: LangFuseInfrastructure: Azure (Container Apps, OpenAI Service)Data: PostgreSQL, pgvectorWhat we offer:Growing international business with 10,000+ subscribersRegular performance-based compensation reviews26 days paid time off1 additional day off for your BirthdayRemote office assistanceService years recognition financial rewardApprovalMax is award-winning B2B software used by businesses around the world to approve bills and expenses.
It streamlines the approval process for decision-makers by replacing paper and email approvals with automated workflows. ApprovalMax integrates with platforms such as Xero, QuickBooks Online, and Oracle NetSuite to unlock powerful efficiencies for approvers and finance teams.
The company is globally recognized and has won ’Xero App Partner of the Year’ four times since 2020 in different countries.
You'll design and build agentic AI systems that automate complex approval workflows for finance teams across 17,000+ businesses.
This is a high-impact role where your work directly shapes how companies handle millions of financial transactions.
What You'll DoDesign, build, and deploy agentic systems using LangGraph and LangChain for workflow automationDevelop and maintain ML models for anomaly detection, fraud prevention, and intelligent document processingBuild evaluation frameworks and implement observability using LangFuseDeploy and scale ML services using Ray Serve or FastAPI + Redis + CeleryWork with vector databases (pgvector) for RAG-based retrieval systemsCollaborate closely with product and engineering to ship AI features with high accuracy
requirements
Contribute to architectural decisions for our growing AI infrastructureWhat You BringRequired:4+ years of production ML experienceStrong Python skills with strict typing practicesHands-on experience building LLM-powered applications (agents, RAG, prompt engineering)Experience with at least one agent framework (LangGraph, LangChain, or similar)Solid foundation in classical ML (classification, regression, anomaly detection)Experience deploying ML models to production (Ray Serve, FastAPI, or equivalent)Familiarity with async processing patterns (Celery, Redis, or similar)Nice to Have:Experience with Azure cloud services (Azure OpenAI, Container Apps)Background in fintech or financial document processingExperience with ML observability tools (LangFuse, LangSmith, Weights Biases)Knowledge of vector databases and embedding modelsExperience with evaluation frameworks for LLM applicationsTech StackLanguages: PythonAgent Frameworks: LangGraph, LangChainDeployment: Ray Serve, FastAPI, Celery, RedisObservability: LangFuseInfrastructure: Azure (Container Apps, OpenAI Service)Data: PostgreSQL, pgvectorWhat we offer:Growing international business with 10,000+ subscribersRegular performance-based compensation reviews26 days paid time off1 additional day off for your BirthdayRemote office assistanceService years recognition financial rewardApprovalMax is award-winning B2B software used by businesses around the world to approve bills and expenses.
It streamlines the approval process for decision-makers by replacing paper and email approvals with automated workflows. ApprovalMax integrates with platforms such as Xero, QuickBooks Online, and Oracle NetSuite to unlock powerful efficiencies for approvers and finance teams.
The company is globally recognized and has won ’Xero App Partner of the Year’ four times since 2020 in different countries.
Discover the company
Explore other offers from this company or learn more about ApprovalMax.
The company
A
ApprovalMax Serbia
