Senior Agentic Engineer

DXC Luxoft; United States; Remote; USD 150,000 - 230,000; Full time

Job summary

Luxoft is seeking a Senior Agentic Engineer to drive Modernization as a Service across multiple projects in the United States. You will launch modernization toolsets, validate initial results, and tailor prompts for production-grade outcomes.

You will collaborate with the modernization team, apply best practices in SQL/DBs, Docker/Kubernetes/Helm, testing, and secure coding to deliver reliable AI-powered solutions for complex business needs.

Qualifications

• Must have hands-on experience with AI agents and coding agents in production environments.
• Deep understanding of how LLM agents operate including context, tools, planning, subagents and typical failure modes.
• Ability to review agent output quickly, identify errors and hallucinations.
• Strong engineering background with 5+ years in full-stack development and production systems.
• Experience with relational databases and SQL; familiarity with graph models (Neo4j) and vector databases.
• Proficient in deploying and debugging Docker, Kubernetes, Helm in real environments.
• Emphasis on testing: unit and integration tests, Testcontainers or similar.
• Understanding of TDD principles and practices.
• Ability to own projects end-to-end, from problem statement to production, with minimal supervision.
• Comfort making decisions with incomplete information and owning outcomes.
• Ability to ramp up quickly in unfamiliar codebases and domains.
• Excellent written and verbal communication to justify decisions.

Responsibilities

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

Skills

AI agents

Coding agents daily

LLM agents understanding

Review agent output quickly

Relational databases

Neo4j graph data models

Vector databases

Docker

Kubernetes

Helm

Testing as a habit

TDD

Owning an area

Decision making with incomplete info

Learn quickly in unfamiliar domains

Explain decisions clearly

Tools

Testcontainers

Job description

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.