Flexible work model
Work from home, from the office, or in a hybrid format that supports focus and collaboration.
About the role
In this role, you will act as the L3 engineering escalation point for a production GenAI Contact Center solution, supporting the application and AI layer above the 24/7 Infrastructure L2 team. You will help keep the service reliable, secure, and trustworthy by diagnosing complex issues in code, configuration, integrations, and AI behaviour, and supporting permanent fixes through the client’s governed change and release process.
Responsibilities
- Provide L3 production support for a GenAI Contact Center solution, ensuring application stability, reliability, security, and user experience
- Investigate and resolve incidents across backend services, APIs, configuration, integrations, Azure-hosted components, and chat/voice orchestration
- Serve as the senior engineering escalation point for complex production issues, helping determine whether they originate in the application, AI layer, infrastructure, Azure platform, telephony, or third-party systems
- Troubleshoot AI-related production issues, including prompt behaviour, grounding, hallucinations, retrieval issues, guardrails, and changes in AI response quality
- Work with AI developers to validate fixes for prompts, RAG flows, orchestration logic, and application defects
- Support controlled changes through the client’s incident, problem, change, release, and deployment processes, including regression checks and production validation before release
- Improve observability using New Relic, Azure Monitor, and Application Insights, including dashboards, telemetry, alert tuning, and incident investigation
- Triage and remediate Checkmarx or other SAST findings using secure-coding practices and governed releases
- Create RCAs, ServiceNow RFCs, Confluence documentation, runbooks, stakeholder updates, and knowledge articles to support problem management and shift repeatable fixes to L2
- Participate in out-of-hours support for critical P1/P2 incidents and planned maintenance when required
- Work Mon–Fri 08:00–17:00 GMT and join an out-of-hours rota for P1/P2 incidents and planned maintenance
Requirements
- Experience with Microsoft Azure, ideally with Azure Container Apps, Cosmos DB, Azure AI Foundry, Azure OpenAI, or Azure Communication Services
- Hands-on use of observability tooling such as Azure Monitor, Application Insights, New Relic, or similar
- Strong application support, debugging, and troubleshooting skills across backend services, APIs, integrations, configuration, and distributed application behaviour
- Practical understanding of GenAI / LLM application behaviour in production — prompts, RAG, grounding, hallucinations, guardrails, and response quality
- Skills to investigate AI-related issues, confirm root cause together with AI developers, validate workarounds, and support permanent fixes
- Working proficiency in at least one of Python, .NET, or Node.js, sufficient to identify defects and implement fixes
- Experience with secure coding and remediation of SAST findings, ideally using Checkmarx or an equivalent tool
- Understanding of ITIL-aligned incident, problem, change, and release processes
- Experience working in a client-facing or managed-services environment, operating within a client’s governance, change, and release processes
- Proficiency in writing clear RCAs, technical documentation, runbooks, knowledge articles, and stakeholder updates in English
- Experience with ServiceNow and production governance (is preferred)
SoftServe is an equal opportunity employer. Qualified applicants will receive consideration regardless of race, color, ancestry, ethnicity, national origin, religion, sex, sexual orientation, gender identity or expression, age, citizenship, disability, health condition, marital or family status, veteran status, or any other characteristic protected by applicable law.
Role Summary
Location
Ukraine
Work type
Remote/Office
Direction
Engineering & Technology
Subdirection
Clouds & DevOps
Tech level
Middle
Apply Now
Fill out the form, and we'll be in touch shortly.
About us
We are a digital engineering and technology consulting company where expertise grows alongside people. For more than 30 years, we have been elevating technology: helping organizations navigate complex business challenges by combining deep engineering knowledge with thoughtful, research-backed innovation. Our teams work across key areas: digital engineering, data and analytics, Сloud, and AI/ML. In each, we deliver practical, scalable solutions rooted in real business needs and measurable human impact.
You bring your perspective and ambition. We create an environment where your work meets clarity, confidence, and purpose.
We offer
Compensation & Benefits
Competitive, market-based pay, benchmarked by role and location — plus health coverage, paid time off, wellness support, and learning opportunities.
People-first Leadership
Approachable leaders who communicate openly, keep teams close to the strategy, and support long-term planning.
Advanced tech communities
Stay close to AI/ML, Cloud, Quantum Computing, IoT, and Robotics communities, with projects built on modern frameworks.