Job Description
About You
Are you looking for an opportunity to work on meaningful, cutting-edge projects at the intersection of agentic AI and responsible business conduct? Did you wonder what it would be like to work at a company where your contribution has a real, measurable impact - and you are rewarded for it?
If you have a passion for building production-grade AI agents, MCP-based tool ecosystems, and data-rich AI workflows, then this is the perfect role for you! We value autonomy, allowing you to bring your innovative ideas to fruition in an inclusive, feedback-oriented environment. Your work on agentic systems will directly contribute to advancing gloabl corporate responsibility through technology.
Your Responsibilities
As our new Senior AI Engineer, you will play a crucial role in developing state-of-the-art agentic systems and AI integrations within RepRisk’s Agentic delivery team. You will contribute to the design, implementation and operation of agentic and AI products within the company. Moreover, you will be:
* Designing and building single- and multi-agent production systems with planning, memory, and tool-use capabilities that meet regulated-industry compliance and auditability standards.
* Building and operating MCP (Model Context Protocol) servers using FastMCP and platform providers such as Databricks or Snowflake, with secure schemas and role-based permissions.
* Developing agentic workflows using LangChain and LangGraph, with robust prompt engineering, tool-use, and multi-agent coordination patterns.
* Implementing testing, evaluation, monitoring, and observability best practices for production agent systems (LangSmith / LangFuse, structured tracing, offline and online evaluation).
* Developing, integrating, and maintaining LLM-powered microservices and APIs (Python, FastAPI, gRPC, Postgres) as part of broader production applications deployed on AWS.
* Identifying, testing, and adopting state-of-the-art advancements in LLMs and autonomous agent architectures (e.g. reflection, planning, multi-agent coordination, AWS Bedrock and Bedrock AgentCore).
* Collaborating closely with the Product Manager, Tech Lead, and domain experts to align technical solutions with user needs and business goals; supporting discovery, proposing improvements, and showing initiative beyond the assigned scope.
Qualifications
You Offer
* Experience: 5+ years of hands-on software engineering experience, with 2-3 years building AI agents in production environments, ideally for high-stakes or regulated industries (finance, legal, healthcare, etc.).
* Education: A Master’s degree or higher in Computer Science, Engineering, Statistics, or a related STEM field (or equivalent practical experience).
* Agentic frameworks: Strong hands-on experience building agents with LangChain and LangGraph (or equivalent orchestration frameworks) — including planning, memory, tool-use, and multi-agent patterns.
* MCP expertise: Proven experience building and operating MCP (Model Context Protocol) servers using FastMCP, or on platform providers such as Databricks or Snowflake, with secure schemas, authentication, and role-based permissions.
* Python & backend: Expert-level Python skills and strong engineering fundamentals across backend systems, APIs, and data pipelines (FastAPI, Postgres / SQLAlchemy, gRPC, async IO, Databricks, testing).
* Observability & evaluation: Proficiency with observability platforms and evaluation frameworks for LLM applications (e.g. LangSmith, LangFuse), performance profiling, and optimization techniques for AI systems.
* Engineering fundamentals: Solid understanding of software design principles (SOLID, DRY, KISS), Clean Code, and common architecture patterns; ability to translate them into maintainable production code.
* Ownership & drive: High sense of product ownership, taking full responsibility for assigned work end-to-end, supporting the Tech Lead and PM in discoveries, proposing improvements to existing services, and showing initiative. Strong responsiveness and reliability.
* Continuous learner: Stays on top of the latest best practices in AI engineering and shares knowledge across the team.
Additionally, the following are a plus:
* AWS Bedrock & AgentCore: hands-on experience with AWS Bedrock and Bedrock AgentCore for managed agent deployments and tool orchestration.
* Kubernetes: experience running containerized workloads on Kubernetes in production.
* ML engineering: experience with classical ML / LLM engineering on large datasets — fine-tuning, retrieval, and summarization pipelines over ESG-scale corpora.
* Coding agents: experience building software solutions with the support of coding agents (Claude Code, Cursor, etc.) and leveraging them to accelerate delivery.
* Mentorship: experience mentoring engineers and providing thoughtful, constructive feedback.
Additional Information
Please note that we will only consider candidates with a valid work permit.