MLOps Engineer – GenAI Platform (AWS)

MLOps Engineer – GenAI Platform (AWS) The place where impact matters Apply now This is us At Avenga, we believe that human creativity empowers technology that matters. Operating globally, our 6000+ specialists provide a full spectrum of services, including business and tech advisory, enterprise solutions, CX, UX and Ul design, managed services, product development, and software development. This is the job We are looking for MLOps Engineer to join a project for a leading telecommunications operator. You will work on the core engine behind a production AI assistant: an agentic system combining information retrieval, LLM orchestration and answer-quality evaluation. The product is designed to move AI-powered customer support from simply answering questions to safely carrying out customer requests, such as placing an order or activating a service, within the requirements of a regulated telecommunications environment. This is an initial 6-month B2B engagement with the possibility of extension. This is you You have hands-on experience building and operating production AI/ML or GenAI platforms in AWS. You have strong practical knowledge of AWS infrastructure, preferably including ECS, IAM and Secrets Manager. You have experience provisioning and managing cloud infrastructure as code, preferably using Terraform. You are proficient in containerisation using Docker and understand production container deployment practices. You have experience setting up cloud security, access controls, secrets management and encryption. You know how to implement monitoring, logging and operational controls for production systems. You can build and expose data and application capabilities through REST APIs. You have practical Python experience and can independently develop production-quality services and automation. You write automated tests as a standard part of development, including unit and integration tests using pytest, fixtures and mocking. You have experience implementing security scanning and improving platform performance and reliability. You are comfortable working with GitHub-based development workflows, including feature branches, pull requests and code reviews. You communicate clearly, take ownership of delivered solutions and proactively identify technical risks and improvements. Nice-to-have skills: Experience operating production systems based on LLMs, AI agents or agentic workflows. Experience with retrieval-augmented generation and improving retrieval quality. Practical knowledge of LLM orchestration, tool calling or AI workflow management. Experience evaluating the quality, accuracy and reliability of LLM-generated responses. Understanding of guardrails and security considerations for production GenAI solutions. Experience working in a regulated, security-sensitive or customer-facing environment. Knowledge of telecommunications products or customer-service processes. This is your role Build and maintain secure, scalable AWS infrastructure supporting a production agentic AI platform. Provision and manage cloud infrastructure using infrastructure-as-code practices, preferably with Terraform. Containerise and deploy AI platform components and supporting services in AWS, including ECS. Configure IAM, secrets management, encryption and other security controls required for a regulated environment. Implement monitoring, logging, security scanning and performance controls across the platform. Develop Python services and REST APIs that expose data and business capabilities to AI-driven workflows. Contribute to the development and operation of retrieval-augmented generation solutions. Support LLM orchestration and the integration of AI agents with external services and business processes. Help evaluate and continuously improve retrieval quality, response accuracy and overall system reliability. Develop and maintain automated unit and integration tests using pytest. Participate in technical design discussions, pull-request reviews and GitHub-based team workflows. Take end-to-end ownership of delivered components and ensure they are production-ready, secure and maintainable. What awaits you at Avenga? At Avenga, everyone matters. We provide equal opportunities in recruitment, career development, and leadership, regardless of race, ethnicity, gender identity, sexual orientation, disability, age, religion, or any other characteristic. We are committed to fostering a work environment where our diverse community of employees, candidates, and business partners actively shapes our growth. By bringing together people from different backgrounds and experiences, we build a workplace where everyone feels free to be themselves while honoring the boundaries of others. Locations Poland Remote status Fully Remote Technology AI Seniority Mid-level Your way in starts here APPLICATION Send us your application, we are ready to hear your story and explore how we can grow together. REVIEW Our team carefully reviews every application with curiosity and care. If your profile isn’t the right fit today, we will keep it in mind for future opportunities that match your skills and ambitions. TALENT ACQUISITION INTERVIEW You will meet our Talent team to talk about your goals and learn more about who we are, what we offer, and how we support our people. TECHNICAL INTERVIEW Our tech interview is all about diving deeper into your expertise and understanding your strengths, how you solve problems, and how you think – no trick questions, just a meaningful conversation. CUSTOMER INTERVIEW For some roles, especially when our clients are closely involved, you might also have a conversation with them – it’s a chance for everyone to align and get to know each other better. JOB OFFER If we both feel it’s the right match, we will send you an offer to join us. And even if it’s not the time just yet, you’ll always hear back from us. WELCOME! Your new team is excited to meet you, support you, and build something great together. Let’s make your first day the start of a journey that shapes a career that matters.