Senior Agentic AI and Harness Engineer

HedgeServ Corporation; Kraków; Hybrid; PLN 210,000 - 320,000; Full time

Job summary

HedgeServ Corporation is seeking a seasoned AI Engineer to design, build, and operate production AI agents for financial operations and enterprise workflows. You will own the agent runtime, orchestration, controls, and observability, driving measurable outcomes with production-grade reliability and security.

The role requires strong Python, API design, and cloud engineering skills, plus hands-on experience delivering LLM/agent-based applications in production. Hybrid work options are available.

Qualifications

• Bachelor's degree or equivalent practical experience.
• 5+ years of software engineering experience.
• 1+ year delivering LLM or agent-based applications in production.
• Strong Python, API design, asynchronous processing, testing, and AWS engineering skills.

Responsibilities

• Runtime: design, deploy, and support reliable production runtimes for AI agents in financial ops and enterprise workflows.
• Orchestration: build/extend agent loops with context assembly, retrieval, memory, tool selection, and state management.
• Controls: enforce authorizations, human approvals, policy checks, validation, retries, and idempotency across agent workflows.
• Enterprise integration: build auditable tool interfaces with least-privilege permissions and defensive measures outside the model.
• Evaluation: create regression tests and evidence tracking for outcomes, tool paths, and costs.
• Observability: monitor production agents and maintain audit trails and performance dashboards.

Skills

Python

API design

Asynchronous processing

AWS

LLM / agent-based development

Testing & automation

DevOps / CI

Education

Bachelor's degree in Computer Science or equivalent

Tools

Amazon Bedrock

Job description

At HedgeServ, we're redefining what's possible in fund administration. With more than $700 billion in assets under administration, we partner with the world's most forward-thinking investment managers - across private equity, private credit, endowments, hedge funds and more - to deliver seamless, tech-enabled solutions that drive performance.

Our proprietary platform, enhanced by machine learning and robotic process automation, gives clients real-time insights and unmatched control over their operations. Alongside our technology, we offer award-winning service through our team-based approach -- led by a deeply experienced team of industry experts. Our solutions span the full investment lifecycle, including fund accounting, middle office, risk, compliance, tax, and investor services.

We're a future-focused company, empowering our people through a robust career development framework, clear career trajectories with structured learning paths, training, and progression plans. We invest in leadership development and in our collaborative culture, creating space for talent to grow. Our corporate values - Relationships, Support, Innovation, and Expertise - create a sense of shared purpose and belonging, and we recognize our employees sit at the core of our success. We continue to innovate and evolve through our employees, working together to achieve our shared vision and mission.

HedgeServ supports employees through a variety of offerings, including remote and hybrid working arrangements, and fully paid comprehensive health and well-being benefits. We've been recognized as an employer of choice, earning a top 100 workplaces designation.

Founded in 2008, HedgeServ has grown into a global organization with over 2,000 experts across the globe, with offices in the United States, Grand Cayman, Ireland, Poland, Bulgaria, Luxembourg, the Philippines, and Australia. We've earned numerous accolades, including Top Overall Administrator, along with #1 rankings for providing alternative asset services in Accounting, Technology, Client Service, Investor Services, Alternative Fund Expertise, Reporting, and Regulatory Expertise.

Department Overview

The AI Engineering team builds secure, reliable, and reusable AI capabilities for HEDGESERV's business and technology platforms, partnering across engineering, security, data, and operations to move solutions into production. We integrate AI into existing workflows and platforms, focusing on measurable outcomes, production discipline, responsible AI, security, human oversight, and evidence-based evaluation.

Role Overview

You will design, build, and operate production AI agents for financial operations and enterprise workflows. In this role, the AI harness is the production layer around the model: the agent runtime, orchestration, controls, evaluation, and observability. You will own this layer, including retrieval, memory, tool execution, workflow state, human approvals, and safety controls. You will bring strong software engineering skills, hands‑on production LLM experience, sound architecture judgment, effective troubleshooting, and cross‑functional collaboration. You will also establish reusable patterns for HEDGESERV engineering teams.

Key Responsibilities

• Runtime: Design, deploy, and support reliable production runtimes for AI agents serving financial operations and enterprise workflows.
• Orchestration: Build and extend agent loops, including context assembly, retrieval, memory, tool selection, execution limits, workflow state, and response validation.
• Controls: Enforce authorization, human approvals, policy checks, validation, checkpoints, idempotency, retries, and exception handling throughout agent workflows.
• Enterprise integration: Build validated, auditable tool and system interfaces with least‑privilege permissions, prompt‑injection defenses, and controls outside the model that isolate reasoning from deterministic execution.
• Evaluation: Build repeatable tests and regression suites for agent outcomes, supporting evidence, and tool‑execution paths; diagnose quality, safety, failures, latency, and cost.
• Observability: Monitor and troubleshoot production agents, maintain audit evidence, and turn operational findings into reusable engineering standards.

Required Qualifications

• Bachelor's degree in a relevant technical field or equivalent practical experience.
• 5+ years of software engineering experience, including at least 1 year delivering LLM or agent-based applications in production.
• Strong Python, API design, asynchronous processing, automated testing, source control, and AWS engineering skills; experience with a managed model platform such as Amazon Bedrock or an equivalent service.
• Hands‑on experience implementing agent loops, context assembly, retrieval, memory, tool selection and limits, durable state, checkpoints, retries, and idempotency.
• Ability to build regression evaluations for outcomes, evidence, and tool paths; enforce least‑privilege tool access and pro