Senior Software Developer

CI&T

. Develop and enhance core components of the AI platform, focusing on model and tenant orchestration, LiteLLM, and integrations with LLM providers .

Posted 10/5/2026full-timeBrazilSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in backend development with a focus on AI platform components, including model orchestration and integrations with cloud services. Proficient in observability practices and capable of troubleshooting complex distributed systems.

Highest-signal resume keywords

Backend Development (Kotlin/Java, Node.js)Azure OpenAI, Azure AI Foundry, AWS Bedrock, GCP Vertex AIObservability and Monitoring (Grafana, Prometheus)Docker and KubernetesLLM Routing and Load Balancing

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Backend Development (Kotlin/Java, Node.js)LLM RoutingLoad BalancingObservability and MonitoringPostgreSQLMongoDBDockerKubernetesGitCI/CD Pipelines

Soft Skills

Investigation and Troubleshooting SkillsCollaboration

Tools & Technologies

GrafanaPrometheusAzure OpenAIAzure AI FoundryAWS BedrockGCP Vertex AILiteLLMLangChainLangGraphSemantic Kernel

Industry Keywords

Generative AIModel Context Protocol (MCP)Retrieval-Augmented Generation (RAG)Distributed SystemsMulti-Tenancy

Tech Stack

Tools & technologies

AWSAzureCloudDockerGoogle Cloud PlatformGrafanaJavaJavaScriptKotlinKubernetesMongoDBNode.jsPostgresPrometheus

About the role

Key responsibilities & impact

Develop and enhance core components of the AI platform, focusing on model and tenant orchestration, LiteLLM, and integrations with LLM providers
Develop new features and maintain and support existing services
Develop governance solutions for models, providers, configurations, tenants, and platform policies
Implement model routing, load balancing, fallback, cost control, and model usage policies
Enhance LiteLLM integrations across inference, routing, and LLM provider layers
Integrate and operate AI models and services on Azure OpenAI, Azure AI Foundry, AWS Bedrock, and GCP Vertex AI
Implement observability through metrics, logs, traces, and dashboards
Investigate and resolve incidents and issues reported by platform users and consumers
Participate in the technical refinement of new features
Identify performance, availability, scalability, and reliability bottlenecks
Develop APIs and integrations between components while maintaining compatibility with existing services
Contribute to architecture evolution and identify technical risks
Document technical decisions, integrations, configurations, and operational procedures
Collaborate with platform consumer teams and guide the proper use of services
Investigate issues by considering the process, application, and business impact

Requirements

What you’ll need

Strong experience in backend development (Kotlin/Java, Node.js)
Knowledge of LLMs and generative AI-based applications
Knowledge of integrating and operating models through Azure OpenAI, Azure AI Foundry, AWS Bedrock, and GCP Vertex AI
Knowledge of LLM routing, load balancing, fallback, streaming, token management, and prompt caching
Knowledge of PostgreSQL and/or MongoDB
Experience with observability and monitoring, including Grafana and Prometheus
Knowledge of distributed application metrics, including latency, throughput, error rate, p90/p95/p99, TTFT, and token consumption
Knowledge of MCP (Model Context Protocol) and related concepts for agent integration
Knowledge of AI Agents / Agentic AI
Knowledge of RAG (Retrieval-Augmented Generation)
Experience with Docker and Kubernetes
Experience with Git and CI/CD pipelines
Experience developing and operating systems in a public cloud environment
Ability to work with distributed systems involving multiple services, applications, clouds, and providers
Investigation and troubleshooting skills, including analysis of logs, metrics, traces, and service behavior
Preferred: hands-on experience with LiteLLM, including Router, deployments, callbacks, customizations, and proxy configuration
Preferred: production experience with Azure AI Foundry, AWS Bedrock, and GCP Vertex AI
Preferred: experience with AI Gateway / LLM Gateway / Model Gateway architectures
Preferred: knowledge of LLM observability, including Langfuse, OpenTelemetry, Prometheus, and Grafana
Preferred: experience with LangChain, LangGraph, Semantic Kernel, or similar frameworks
Preferred: knowledge of vector databases and semantic search mechanisms
Preferred: experience with guardrails, security, and data protection in AI applications
Preferred: knowledge of OAuth2, API Keys, RBAC, multi-tenancy, and access control
Preferred: experience with Helm and GitOps
Preferred: experience developing tools or skills/agents for AI Coding, such as Claude Code

Benefits

Comp & perks

Health and dental insurance
Meal and food allowances
Childcare assistance
Extended parental leave
Partnerships with gyms and health and wellness professionals through Wellhub (Gympass) and TotalPass
Profit Sharing and Results Participation (PLR)
Life insurance
Continuous learning platform (CI&T University)
Discount club
Free online platform dedicated to promoting physical health, mental health, and well-being
Pregnancy and responsible parenting course
Partnerships with online course platforms
Language learning platform
Support and accommodations for people with disabilities
Dedicated Health and Well-being team
Inclusion specialists and affinity groups