AI Platform Engineer, Agent Systems IRC296274

GlobalLogic; Kraków; Hybrid; PLN 133,920 - 200,880; Full time

Benefits offered by this job

Comprehensive benefits package

Flexible work opportunities

Career development programs

Job summary

GlobalLogic is seeking an experienced professional to lead the design of an orchestration loop for an innovative agent platform in music production. You will shape how the engine's capabilities integrate with tools and act on workflows, while building systems that ensure agent coherence over extended creative processes.

The ideal candidate has a strong background in LLM systems, with over five years of experience and proficiency in programming languages such as TypeScript and Python. Join us to be part of cutting-edge projects that harness the power of technology to shape the future of music production.

Qualifications

• Five or more years shipping production platform or infrastructure software.
• Eighteen or more months of experience building LLM agent systems.
• Demonstrated experience building context, memory, or state-management systems.
• Strong proficiency in TypeScript and Python.

Responsibilities

• Lead the design of the orchestration loop.
• Define how the engine’s capabilities are exposed.
• Build the skills runtime for transforming a general-purpose model.
• Create systems for keeping agents coherent across long workflows.
• Design architecture for adding new tools and skills.

Skills

Proficiency in TypeScript

Proficiency in Python

Experience designing tool interfaces

Understanding of orchestration loops

Experience with LLM agent systems

Job description

Description

The company is building the agent platform for professional music production: the orchestration layer, tool interfaces, skills runtime, and context architecture that allow any AI agent to reason about and act on a music‑production workflow. The object model is a song. The users are producers, musicians, and creatives, and the domain has real‑time constraints, deep semantics, and no existing playbook.

Responsibilities

You will lead the design of the orchestration loop, define how the engine’s capabilities are exposed to models, build the skills runtime that transforms a general‑purpose model into a domain specialist, and architect the context and memory systems that keep agents coherent across long creative sessions.

• Tool interfaces: Define how the engine’s capabilities are exposed to LLMs as structured, discoverable tools, including schemas, semantic descriptions, scoped tool sets, input validation, and output parsing that a model can reliably produce and the harness can reliably consume.
• Orchestration and control flow: Design and build the harness—including step sequencing, retries, timeouts, error recovery, fallback paths, and multi‑agent coordination—evaluating whether to build it in-house, adopt a framework, or extend an existing one.
• Skills runtime: Design the format, packaging, loading, and execution layer for the structured domain knowledge that turns a generic model into a music‑production specialist.
• Context, memory, and state: Build systems that keep agents performant and coherent across long, multi‑step creative workflows, including context compaction, short‑term working memory, durable cross‑session memory, session state persistence, continuity across disconnects, and sub‑agent delegation.
• Extension points: Design the harness so new tools, skills, and middleware can be added without modifying the core runtime.
• Evaluations, observability, and failure analysis: Build and own the platform‑level evaluation surface, observability, and feedback loop that converts failed agent runs into targeted harness changes.
• Ongoing simplification: Audit the harness regularly and remove components no longer required as models improve.

Qualifications

• Five or more years shipping production platform or infrastructure software that other engineers have built on top of.
• Eighteen or more months of production experience building LLM agent systems—covering orchestration loops, tool use, and context management—whether on a provider‑agnostic framework such as LangGraph or a custom harness, with the ability to articulate lessons learned.
• Demonstrated experience designing tool interfaces for LLM consumption, explaining what makes a tool schema discoverable and usable by a model versus merely technically correct.
• Demonstrated experience building context, memory, or state‑management systems beyond framework defaults, including compaction, durable memory, or session persistence, and diagnosing agent failures from raw execution traces to make targeted harness changes.
• Strong proficiency in TypeScript and Python.
• Experience with the Model Context Protocol (MCP) or similar tool‑connectivity standards.

Nice to Have (not Required)

• Background in music production, audio engineering, or another creative‑tool domain—including as a serious hobbyist.
• Experience with real‑time audio systems, professional audio software, or other latency‑sensitive environments.
• Experience making a complex desktop or professional application agent‑accessible in any domain with a rich object model (DAW, IDE, design tool, CAD).
• Experience building middleware or hook architectures that allow others to customize agent behavior without modifying core code.

This Role Is Not

• LLM integration engineering: this role does not wire models to the DAW or build end‑user AI features; it builds the platform those features run on.
• Machine‑learning or model engineering: this team does not train models; it builds the systems that agents run on.
• Research: this team applies current research in production; original research happens elsewhere in the company.

What We Offer

Empowering Projects

With 500+ clients spanning diverse industries and domains, we provide an exciting opportunity to contribute to groundbreaking projects that leverage cutting‑edge technologies, engineering digital products that positively impact people’s lives.

Empowering Growth

We foster continuous learning, professional development, and timely support through a dedicated Learning & Development team, ensuring growth and success for every consultant.

DE&I Matters

We deeply value and embrace diversity, equality, and an inclusive, empowering work environment.

Career Development

Our culture emphasizes career development, offering abundant opportunities for growth, regular interaction with teams, and recognition of engagement and motivation.

Comprehensive Benefits

In addition to equitable compensation, we provide a comprehensive benefits package that prioritizes the overall well‑being of our consultants.

Flexible Opportunities

We prioritize work‑life balance by offering flexible opportunities tailored to lifestyle, including relocation and rotation options for diverse cultural and professional experiences in different countries.