Senior GenAI Full-Stack Engineer
Codurance
Job description
About the role
Codurance is looking for a Senior GenAI Full-Stack Engineer based in Brazil. You will design and extend production-grade LLM applications and agentic workflows, build the conversation-machine substrate, and evolve the AI systems behind the Support Assistant chatbot and the Agent Support Assistant copilot used by customer support agents.
Key responsibilities
- Build and maintain production LLM apps and agentic workflows with NestJS, XState v5 and the OpenAI SDK, covering RAG, intent detection, clarification, fulfillment, escalation, tool use and human-in-the-loop state machines.
- Maintain the conversation-machine substrate: guard/action registries, flow validation (ajv), DB-driven flow configs and design-time tooling.
- Integrate with MCP servers (Model Context Protocol) for tool use and agentic behavior.
- Evaluate, benchmark and tune models across OpenAI, Gemini, Anthropic and future providers, owning model selection on quality, latency, throughput, reliability and cost.
- Troubleshoot production issues such as hallucinations, retrieval failures, prompt regressions, model drift, token inefficiency, latency bottlenecks and provider outages.
- Build resilience: retries, fallback routing, caching, streaming, rate limiting and provider routing.
- Instrument and tune model quality with Langfuse (tracing, evals, prompt management), evaluation datasets, A/B testing, prompt versioning and telemetry.
- Manage async workloads with BullMQ and Redis caching, and PostgreSQL persistence via Kysely.
Required profile
- Proven experience building and operating production LLM-powered systems such as chatbots, AI assistants, agent copilots, RAG systems or orchestration platforms.
- Production AI experience: prompt engineering, RAG pipelines, agent design, tool calling, model evaluation and observability, with shipped features rather than prototypes.
- Full-stack depth across NestJS APIs, React UIs, databases, infrastructure and production operations.
- Ability to evaluate trade-offs between quality, latency, reliability, throughput and cost, and to troubleshoot AI systems across prompts, retrieval, model configuration, infrastructure and code.
- State machine thinking; XState or similar experience is a strong signal.
- Strong testing culture with unit, integration and contract tests.
- Experience in a monorepo with multiple interconnected services.
Required skills
- TypeScript and Node.js, with strict-mode fluency
- NestJS, React, PostgreSQL, Redis, BullMQ, Kysely, ajv
- REST API design, async patterns (queues, events) and caching strategies
- Plus: MCP, Langfuse, model evaluation across providers, AI gateways such as Portkey, semantic search, low-latency streaming, and customer support or gaming product background
Questions fréquentes
Why are you reporting this job?
Explore further
Salaries, guides and searches in Brazil.
Salaries by job title
Apply in 30 seconds
Enter your email to apply. An account will be created automatically.
By continuing, you accept our terms of use.
Already have an account? Login
A question about this job?
Ask it here: you will get the full job summary by e-mail, right away.
Published 4 hours ago
Expires 1 month from now
4 views · 0 interested
Boost your chances
Upload your CV — we will match you with relevant openings.
Analyzing your CV...
Codurance