Machine Learning/AI Engineer

Ambush is a people first company where talented, thoughtful individuals come together to build meaningful products and lasting partnerships. We believe the best work happens when people feel supported, trusted and empowered to bring their full abilities to the table.

Since 2015, because of our people first and long term mindset, we have grown into a partner relied on by some of the best companies in the world. We combine strong engineering, design and strategy with a growing strength in AI to help our clients see what is next and achieve bigger outcomes.

At the heart of everything we do is our team. We collaborate, take risks, lift each other up and take pride in doing work the right way, not settling for a quick makeshift solution. If you join Ambush, you join a group of people who want you to succeed and who show up for each other every day.

We believe in and expect real teamwork, a constant drive to be better, and delivering meaningful long term outcomes that we can be proud of together.

Role Summary

We are seeking a hands-on AI Engineer to design, build, and deploy enterprise-grade GenAI and Agentic AI solutions for complex financial services workflows. This role focuses on building the complete workflow around an AI model, not just prompts or chatbots. That workflow includes exception classification, root-cause analysis, impact assessment, and remediation across large-scale transaction and data-processing environments. The ideal candidate combines strong Python, SQL, and software engineering fundamentals with practical experience taking LLM and agentic applications beyond proof of concept and into production.

Key Responsibilities

• Build AI workflows for exception classification, triage, root-cause analysis, impact assessment, and remediation recommendations.
• Develop agentic workflows involving orchestration, tool/function calling, state management, and human-in-the-loop validation.
• Correlate new exceptions with historical issues, known root causes, business rules, and transaction/data attributes.
• Build Python and SQL-based services to query, transform, and analyze large structured enterprise datasets.
• Develop reusable tools and services that AI agents can invoke for retrieval, investigation, analysis, and workflow execution.
• Integrate AI applications with enterprise APIs, databases, workflow/ticketing platforms, and internal data sources.
• Apply RAG and context retrieval over regulatory documents, historical knowledge, and issue repositories.
• Implement confidence scoring, validation, guardrails, and traceability for AI-generated outcomes.
• Build backend services and APIs using Python (FastAPI) and deploy them on a major cloud platform.
• Implement testing, logging, evaluation, observability, and production engineering practices.
• Collaborate with onshore and offshore engineers, architects, business analysts, data engineers, and application teams.

Requirements

• Strong hands-on proficiency in Python backend development and building production-grade services with frameworks like FastAPI.
• Strong SQL and data analysis skills, with experience working with large structured datasets.
• Proven experience building LLM/GenAI applications that went beyond proof-of-concept chatbots.
• Hands-on experience with at least one agent or workflow orchestration framework, such as LangGraph, Google ADK, CrewAI, AutoGen, Semantic Kernel, or an equivalent custom framework.
• Solid understanding of tool/function calling and how to design reusable tools for agents.
• Experience with RAG and retrieval techniques.
• Experience implementing LLM evaluation, guardrails, and validation for AI outputs.
• Solid software engineering fundamentals: Git, testing, code review, and CI.
• Hands-on experience deploying backend services on a major cloud platform (AWS preferred, GCP or Azure considered).
• Strong analytical, debugging, and root-cause analysis skills.
• Very good English and the ability to collaborate effectively across distributed engineering and business teams.
• A pragmatic approach to AI, knowing what belongs in deterministic logic and where an LLM delivers tangible, measurable value.

Nice to Have

• Experience in financial services, especially regulatory reporting, capital markets, trade lifecycle, post-trade processing, transaction reporting, reconciliations, exception management, or risk and controls.
• Familiarity with regulations such as EMIR, MiFID II, or SFTR.
• Experience with Model Context Protocol (MCP) and reusable agent tool interfaces.
• Knowledge of Knowledge Graphs, Graph RAG, or data lineage concepts.
• Experience with vector databases, hybrid search, or re-ranking.
• Experience with AI observability and evaluation frameworks.
• Experience with AWS AI services (Bedrock, SageMaker) and infrastructure tooling (Docker, Kubernetes, Terraform).
• Ability to translate requirements into clear specifications, tasks, and acceptance criteria before implementation (Spec-Driven Development).
• Disciplined use of Claude Code or similar AI coding assistants.
• Basic React or frontend integration experience.