MindBridge is the global leader in AI-powered financial risk intelligence. Our platform, MindBridge AI is enabling finance and audit professionals to build the AI-powered finance department of the future. With over 120 billion financial transactions analyzed with MindBridge's AI, we set the standard for innovation, scalability, and customer satisfaction.
At MindBridge, we're driven by innovation and excellence, united as a team to revolutionize financial integrity. Here, your ideas matter, and your efforts make a meaningful impact. If you're passionate about using AI to drive positive change, MindBridge is the perfect fit. What distinguishes us is our unwavering commitment to our values: Innovation, Collaboration, and Integrity. These principles foster a vibrant workplace culture, where appreciation and a strong sense of community flourish.
About the Role
We're looking for a Senior Agentic AI Developer to join MindBridge's Applied AI team. You'll design, build, and operate production-grade LLM-powered agent systems that perform multi-step reasoning, tool use, and goal-oriented workflows. Reporting to the AI Architect, you'll own the full implementation lifecycle, from prototype to production, ensuring systems are robust, scalable, and secure.
What You'll Do
Agentic AI Implementation
Design and implement LLM-powered agentic systems that perform multi-step reasoning, tool use, and autonomous workflows Build agent pipelines using frameworks such as LangGraph, LangChain, AutoGen, or Semantic Kernel, with a focus on reliability and maintainability Implement robust patterns for RAG, memory, and planning, integrating vector databases and external tools so agents can act on real enterprise data Harden agent behavior with defensive coding: timeouts, retries, circuit breakers, and safe fallbacks for tool failures Implement guardrails and policies to mitigate prompt injection, data leakage, and unsafe actions Collaborate with the AI Architect to translate high-level designs into production-grade implementations MLOps & Production Infrastructure
Own the end-to-end lifecycle of agentic AI services: packaging, deployment, rollout, and ongoing maintenance Build CI/CD pipelines and infrastructure-as-code for safe, repeatable deployments and rollbacks Integrate with cloud platforms (AWS, GCP, Azure) and container orchestration (Docker, Kubernetes) to ensure scalability and cost efficiency Implement observability for agents: structured logging, tracing of tool calls, metrics for latency, cost, task success rate, and safety events Collaborate with platform and security teams to ensure compliance with governance, access control, and audit requirements Software Engineering & Integration
Develop and maintain backend services and APIs that expose agent capabilities to internal and external consumers Integrate agents with existing systems (databases, data warehouses, CRMs, SaaS tools) to build end-to-end workflows Ensure code quality through strong engineering practices: type hints, automated testing, code review, and documentation Implement security and multi-tenancy patterns around agent services, including authentication, data isolation, and rate-limiting Serve as the bridge between experimental prototypes and production systems
What You'll Bring
Required
5+ years of professional software engineering or AI/ML engineering experience, including building and operating production services Strong Python proficiency and familiarity with AI/ML and backend stacks (FastAPI, PyTorch, Hugging Face, or similar) Hands-on experience integrating LLMs into applications: prompt engineering, embeddings, RAG, or fine-tuning Practical experience with at least one agentic/LLM framework (LangGraph, LangChain, AutoGen, Semantic Kernel, or equivalents) Proven track record of shipping production systems on a major cloud provider (AWS, GCP, Azure) with containerization and orchestration Strong understanding of software engineering best practices: version control, automated testing, CI/CD, monitoring, and incident response Preferred
2+ years working directly with LLM-based or agentic systems (multi-step agents, tool orchestration, autonomous workflows) Experience designing or operating multi-agent architectures (planner-executor-critic patterns, supervisor agents) Familiarity with vector databases (Pinecone, Weaviate, FAISS) and data platforms (warehouses, streaming) Exposure to AI governance and security (data privacy, access control, audit logging) in enterprise environments Experience with front-end or full-stack development (React, TypeScript) to collaborate on end-to-end user experiences Contributions to open-source agentic AI tools or internal frameworks
How You'll Succeed
You ship and own systems end-to-end, from code to production reliability You write clean, maintainable code that others can understand and extend You communicate clearly with cross-functional partners and document designs and trade-offs You stay current with LLM and agentic AI developments, recommending tools that improve velocity and robustness Requirements Contingent on Employment
Fulfill requirements necessary to obtain and clear a full background check Why You'll Love Being Part of Our Team:
Competitive Compensation and Equity
Flexible Work – Hybrid or Remote
Comprehensive health benefits and wellness programs
Professional development opportunities
Flexible Time Off
Company Matched Retirement Plans
Unplug and recharge - 4 company-wide digital detox days annually
Equal Opportunity at MindBridge:
At the heart of our global success lies commitment to diversity and inclusion. We rigorously enforce an equal opportunity policy in all aspects of employment, championing merit and qualifications as our benchmarks. MindBridge is a proud equal opportunity employer, embracing applicants of all backgrounds without regard to race, nationality, religion, gender, disability, or any other factors.
At MindBridge, we are committed to providing an accessible candidate experience. If you require accommodations during the interview process or beyond, please inform us. We will work with you to provide necessary support and reasonable accommodations while maintaining confidentiality. Your comfort and participation are paramount to us.
Please be advised that we may use AI tools in the processing of your application.
