AI Forward Deployment Engineer

Posted 7 hours ago

This is a fully remote position, open to applicants in Poland.

📋 Description

• Design, develop, and maintain production AI agents and features powered by AI.

• Create and manage agentic systems from start to finish, which includes task decomposition, tool design, context and memory strategies, orchestration, human-in-the-loop checkpoints, and fallback behaviors.

• Construct the retrieval and grounding layer, covering document processing, chunking, hybrid search, and citations.

• Deploy and manage AI workloads on Azure AI Foundry, including model deployments, endpoints, content safety, private networking, and cost and quota oversight.

• Utilize Claude Code as a primary engineering tool and set standards for other teams.

• Develop evaluation suites and golden datasets; assess accuracy, latency, cost, and tool-call correctness.

• Implement AI guardrails, defenses against prompt injection, and handling of PII alongside Platform Engineering.

• Deliver through CI/CD with versioned prompts and agent definitions, along with tracing and token/cost observability.

• Assist teams in adopting shared AI services by reviewing designs, troubleshooting integrations, and documenting reusable patterns.

• Set KPIs for adoption, quality, and cost-per-outcome.

• Engage fully in the agile process, manage sprint tasks, log time worked, and keep details up to date.


⛳️ Requirements

• 4–6 years of experience in software engineering, with a minimum of 2 years working with large language models in production environments.

• Practical experience in shipping agentic systems, including multi-step tool usage, structured outputs, state and memory management, and error recovery.

• Proficient in using Claude or a similar frontier model platform, including APIs, tool usage, and agent SDKs.

• Daily hands-on experience with AI-assisted development tools, particularly Claude Code.

• Expertise in retrieval engineering: embeddings, vector and hybrid search, reranking, and assessing retrieval quality.

• Knowledge of evaluation and observability for non-deterministic systems, including offline evaluations, human review loops, tracing, and cost instrumentation.

• Strong proficiency in Python, along with one of TypeScript, C#, or Java.

• Experience with Azure AI Foundry or Azure OpenAI.

• Understanding of Azure fundamentals, including App Service or Function Apps, Key Vault, Storage, Entra ID managed identities, and Application Insights.

• Familiarity with CI/CD processes using Azure DevOps, including YAML pipelines, multi-stage deployments, and secret management.

• Knowledge of REST and asynchronous API design, as well as integration with enterprise record systems.

• Experience with databases (both SQL and NoSQL) and vector stores; solid understanding of Git and code review practices.

• Strong security judgment applied to AI.

• Excellent communication skills, capable of explaining AI design decisions and trade-offs to non-specialists.

• Experience working in an agile AI Development Life Cycle (AIDLC) in a fast-paced environment.

• A Bachelor's degree in Computer Science or a related field, or equivalent practical experience.


🏝️ Benefits

• Equal Opportunity Employer.

• Inclusive environment for all colleagues.

People also viewed

Logicalis Spain7 hours ago

Arquitecto/a de plataforma – Desarrollo, DevOps

ES flagSpain OnlyFull-timeDevOps & Site Reliability Engineer (SRE)
ApplyView job
Visual Concepts7 hours ago

Lead Engineer, Dev Ops

US flagUnited States, +7 more locationsFull-timeDevOps & Site Reliability Engineer (SRE)$138.6k – $194.1k/year
ApplyView job
Sureify7 hours ago

Senior DevOps Engineer

US flagUnited States, +1 more countryFull-timeDevOps & Site Reliability Engineer (SRE)$130k – $165k/year
ApplyView job
Honest Health7 hours ago

Cloud and DevOps Engineer

US flagUnited States OnlyFull-timeDevOps & Site Reliability Engineer (SRE)$105.6k – $122.7k/year
ApplyView job
SafetyChain Software7 hours ago

Principal CloudOps and DevOps Engineer

US flagUnited States OnlyFull-timeDevOps & Site Reliability Engineer (SRE)$150k/year
ApplyView job
Nebius Group8 hours ago

Senior Site Reliability Engineer, YTsaurus

NL flagNetherlands, +3 more countriesFull-timeDevOps & Site Reliability Engineer (SRE)
ApplyView job

Never miss a great job!

Get handpicked remote jobs straight to your inbox weekly.

Trusted by 7,400+ designers