Senior Agentic Engineer

Luxoft; España; A distancia; EUR 90.000 - 120.000; Jornada completa

Descripción de la vacante

Luxoft in Spain is seeking a Senior Agentic Engineer to join our MaaS modernization program. You will launch toolsets, validate results, and tailor prompts to drive production-grade AI agents across projects.

The role emphasizes ownership, rapid learning of unfamiliar code, and delivering robust, secure agentic solutions with a strong testing habit and experience with Docker/Kubernetes.

Formación

• 5+ years of professional full-stack software development.
• Experience deploying with Docker, Kubernetes, and Helm.
• Knowledge of SQL and graph DBs (Neo4j).
• Familiar with TDD and testing.
• Ability to own end-to-end features.
• Experience with AI agent tooling and prompts.

Responsabilidades

• Launch modernization toolset.
• Perform initial result validation.
• Customize and adjust prompts.
• Troubleshoot, debug, and resolve prompt issues.
• Collaborate with modernization team to meet project goals.

Conocimientos

AI agents

Coding agents daily

LLM agents understanding

Review agent outputs

Full-stack development 5+ yrs

Relational databases & SQL

Neo4j graph models

Vector databases

Docker

Kubernetes

Helm

Testing (unit/integration)

TDD concepts

Ownership & decision making

Learn quickly in unfamiliar code

Explain decisions in writing & in code

Herramientas

Neo4j

SQL

Testcontainers

LLM APIs (Anthropic/OpenAI)

Descripción del empleo

Project description

Modernization as a Service (MaaS) is a horizontal practice, supporting all business verticals in the company.We are looking for a Senior Agentic Engineer who will be able to work with different modernization projects.

Responsibilities

• Launch modernization toolset
• Perform initial result validation
• Customize and adjust prompts
• Troubleshoot, debug, and resolve prompt issues
• Collaborate with modernization team members to align with project goals and deliver high-quality solutions

SKILLS

Must have

• AI agents:
• Daily work with coding agents (Claude Code, Cursor, Codex or similar) as your main way of writing code, not an experiment.
• Understanding of how LLM agents work: context, tools, planning, subagents, typical failure modes.
• Ability to review agent output quickly and critically, catching errors and hallucinations.
• Engineering background:
• 5+ years of professional software development as a full stack developer, with systems taken to production and supported there.
• Relational databases and SQL; understanding of graph data models (Neo4j) and vector databases.
• Docker, Kubernetes, Helm: you deploy and debug them yourself.
• Testing as a habit: unit and integration tests, Testcontainers or similar.
• Understanding of TDD aspects.
• Soft skills:
• Owning an area on your own, from an unclear problem statement to production, without someone else breaking it into tasks.
• Willingness to make decisions with incomplete information and to own the outcome.
• Ability to get up to speed quickly in unfamiliar code, technology or business domains.
• Ability to explain a decision and its limits in writing and in person.

Nice to have

• Experience with LLM provider APIs (Anthropic, OpenAI, Bedrock) or a gateway such as LiteLLM.
• R&D experience: hypotheses, prototypes, experiments and data-driven decisions on problems with no known answer.
• Mainframe: COBOL, CICS, JCL, DB2, IMS, PL/I, HLASM, CA Gen, z/TPF; 3270 and z/OSMF.
• Experience building evals for non-deterministic systems: regression suites, metrics, comparison of models and prompts.
• Knowledge of threats to agents and the code they write: prompt injection, secret leakage, excessive permissions, poisoned dependencies and MCP servers (OWASP Top 10 for Agentic Applications).
• Secure work with coding agents.