Generative AI Engineer

Andela exists to connect brilliance and opportunity. Since 2014, we have been dedicated to breaking down global barriers and accelerating the future of work for both technologists and organizations around the world. For technologists, Andela offers competitive long-term career opportunities with leading organizations, access to a global community of professionals, and educational opportunities with leading technology providers.At Andela, we're deeply passionate about creating long-lasting and transformative growth opportunities for all - and doing it in an E.P.I.C. way! We're excited to continue building our remote-first team with incredible people like you. After applying for this role, you will join our Andela Community of brilliant technologists by passing a technical screening and live interview. As a community member, you'll have access to a multitude of exclusive technologist roles.Join Andela today to access this opportunity and more in our global marketplace!Our roles are typically filled at lightning speed, so if you're considering applying, get your application in quickly! About the clientA global provider of professional information, software solutions, and services focused on delivering high-value tools for businesses and professionals. The company emphasizes innovation through AI-driven technologies, strong engineering practices, and cloud-based platforms, fostering a collaborative and execution-focused culture that prioritizes speed, ownership, and scalable product development. About the roleThis is a senior-level AI Engineer position within a platform engineering team, focused on designing and delivering production-grade AI-powered software and developer tools. The role combines backend engineering, cloud infrastructure, and generative AI expertise to build scalable APIs and SDKs. You will work closely with product and platform teams to accelerate delivery using AI-assisted development tools. The position requires strong ownership, hands-on execution, and the ability to ship reliable, high-quality systems quickly. It is ideal for engineers who thrive in fast-paced, collaborative environments and are deeply experienced in Python and cloud platforms. Responsibilities • Architect and implement secure, scalable Web APIs in Python (e.g., FastAPI), including authentication/authorization, rate limiting, and observability. • Design, develop, test, version, and publish Python SDKs, including semantic versioning, strong documentation, and samples. • Leverage AI-assisted development tools to accelerate coding, refactoring, test generation, and code reviews while enforcing standards. • Build, deploy, and operate applications on Azure and/or AWS (e.g., Azure Functions, App Service, AKS; or AWS Lambda, ECS/EKS), using infrastructure-as-code where appropriate. • Develop AI solutions using LLMs and RAG (e.g., Azure OpenAI Service, Amazon Bedrock, embeddings, vector stores), including prompt design, evaluation, and guardrails. • Implement robust testing and validation (unit, integration, contract, and load tests) and ensure high code coverage and quality gates. • Instrument services with logging, metrics, tracing, and dashboards; proactively identify and remediate bottlenecks and defects. • Collaborate with product, data, security, and platform teams to define requirements, ship features, and meet SLAs/SLOs. • Mentor developers on Python best practices, AI-assisted development, performance, security, and operational excellence. Must have skills • 15+ years of professional software development experience • 7+ years of experience with Python • 5+ years building and operating Web APIs at scale (FastAPI, Django, or Flask), including OpenAPI/Swagger and contract-first design • 2+ years deploying to cloud platforms (Azure and/or AWS) using services such as Azure Functions/App Service/AKS or AWS Lambda/ECS/EKS, and infrastructure-as-code (Bicep/ARM/Terraform) • Hands-on experience with Generative AI in production or pre-production, including prompt engineering, LLM integration, RAG pipelines, and model/response evaluation • Demonstrated use of AI coding assistants (e.g., GitHub Copilot) to accelerate delivery • Strong experience designing, versioning, and distributing SDKs (packaging, semantic versioning, PyPI) • Proficiency with CI/CD (GitHub Actions, Azure DevOps), automated testing (pytest), and quality tooling (ruff/black/mypy) • Solid understanding of security and compliance (OAuth2/OIDC, JWT, Secrets Management) • Observability experience with centralized logging and tracing (OpenTelemetry, Azure Monitor, CloudWatch) • Data layer experience with SQL/NoSQL and vector databases (e.g., Azure AI Search, OpenSearch, Pinecone) • Strong ownership mindset, ability to work autonomously, and execution-driven approach • Leadership experience and ability to mentor teams. Conditions • 100% Remote role, with at least 6 hours overlap with CST. • Contractor role – 6-month contract, renewable. • Full-time dedic