GenAI Software Engineer (Backend & API Integration)

Your profile
To feel comfortable in the position, knowledge of the following is required:
• Solid software engineering foundation (3-7+ years, depending on seniority): API design, integration patterns, concurrency/asynchronous programming, good coding practices (Clean Code, SOLID).
• Experience with Python and backend frameworks (FastAPI, Flask, Express, etc.).
• Advanced Git (branching model, pull requests, code review) and CI/CD in at least one of: GitHub Actions / GitLab CI / Azure DevOps / Jenkins.
• Cloud (at least one: Azure, AWS or GCP) with deployment of containerized workloads (Docker; Kubernetes desirable).
• Integration with GenAI/LLM services (Azure OpenAI, OpenAI, Vertex AI, Bedrock): API consumption, authentication, cost and limit management, prompting and basic evaluation.
• Practical knowledge of RAG (embeddings, vector stores such as FAISS, pgvector, Pinecone) and orchestrators (LangChain/LlamaIndex/Semantic Kernel).
• Testing (unit/integration/contract), monitoring (e.g., OpenTelemetry), and basic API security (OAuth2/OIDC, secrets, rate limiting).
• Professional English (working with documentation and international teams).
• LLMOps/MLOps: MLflow, Weights & Biases, Prompt Flow/Azure AI Studio evals, experiment tracking and evaluation dashboards.
• Product mindset and obsession with production quality.
• Collaboration with multidisciplinary teams (architecture, data, security, business).
• Continuous learning in a highly dynamic environment (new models, frameworks, evaluations).
• Clear communication and documentation of decisions.

Additionally, it would be great if you have experience in:
• Infrastructure as Code (Terraform), advanced Kubernetes (ingress, autoscaling, service mesh), event-driven architectures (Pub/Sub, Kafka).
• Observability and reliability: SLO/SLA, alerting, graceful degradation, chaos testing.
• Security and compliance in GenAI: drafting guardrails, PII filtering, content controls.
• Experience with Agentic AI (planning, tools, memory, agent teams).

We value all applications and offer on-site, online, and certified training. Even if you do not meet 100% of the requirements, we want to meet you!

What will you like about working here?
- Varied and challenging projects: You will work on multi-sector challenges, avoiding routine and exposing yourself to diverse technologies.
- Flexibility and hybrid model: Culture oriented towards work-life balance.
- Continuous learning:
o Training in cloud technologies, data governance, visualization...
o Real participation in projects with generative AI, Business AI and emerging data technologies.
- Client diversity and constant innovation: Projects with real impact with leading organizations.
- Collaborative and inclusive environments: Dynamic, multicultural teams oriented towards growth.
- Professional growth and technical challenge: Autonomy, mentoring, certifications and opportunities to expand your role within the Data & AI area.

What will you do on the project? What will your role be?
• Drive the design and development of AI applications and services that integrate language models (LLMs) and Generative AI capabilities in cloud environments (Azure/AWS/GCP), with modern engineering practices (CI/CD, testing, observability, security) to bring robust solutions to production (RAG, agents, process automation) aligned with reliable GenAI delivery frameworks
• Design and develop backend services (REST/GraphQL) and microservices that integrate LLMs (Azure OpenAI, OpenAI, Vertex AI, Amazon Bedrock) and tools/functions to execute actions on internal/external APIs.
• Build RAG pipelines (ingestion, chunking, embeddings, vector storage, retrieval) and agents with orchestrators (LangChain, LlamaIndex, Semantic Kernel, or others) and tool/function calling mechanisms.
• Implement CI/CD (GitHub Actions, GitLab CI, Azure DevOps, Jenkins), containers (Docker, Kubernetes) and observability (logging, metrics, tracing).
• Ensure quality: TDD/BDD, unit/contract/integration testing; define quality gateways (linting, SAST/DAST, dependency scanning).
• Apply LLMOps/MLOps: versioning of prompts and artifacts, quality evaluation (accuracy, groundedness, toxicity), monitoring (latency, cost, drift), and guardrails (policies, content, PII).
• Collaborate with architecture, data, security and business teams to land non-functional requirements (scalability, resilience, cost) and AI governance/ethics (data access, compliance).
• Document decisions (ADRs), develop reusable playbooks and support code reviews and mentoring of more junior profiles.
• Contribute to internal accelerators and reusable components aligned with Data & AI capability frameworks.