Aldelia is a Franco-British multinational focused on HR solutions and outsourced services.
About Our Client
Our client is a global data and artificial intelligence consultancy with a strong presence in Brazil. It helps large companies across a range of industries turn data into tangible results, from strategy to the implementation of AI, analytics, and digital marketing solutions. With a multidisciplinary team of consultants, engineers, and data scientists, it works on high-impact projects and values a collaborative culture focused on continuous learning and innovation.
The Role
Our client is looking for a Senior AI & Agentic Engineer: a full-stack engineer who takes AI features from idea to production. The professional will design and build the interfaces, services, and agentic systems at the heart of client work, such as conversational applications over enterprise data, multi-step agents that automate business workflows, and the retrieval and data pipelines that support them.
This person will own components end to end: the React front end, the Python or Node service behind it, the RAG pipeline feeding it, and the evaluations proving it works. The role combines breadth and depth, from front end to cloud deployment, together with strong expertise in at least one major AI platform: Google (Gemini), Anthropic (Claude), or OpenAI. It involves direct client exposure and supporting the professional development of junior engineers.
Key Responsibilities
Build full-stack AI applications, end to end
- Develop user-facing interfaces in TypeScript/React and the backend services and APIs behind them in Python or Node
- Implement agentic behavior: orchestration, tool and function calling, memory, and guardrails
- Build retrieval-augmented generation (RAG) pipelines: ingestion, chunking, embeddings, vector and hybrid search
- Connect AI systems to enterprise data and applications via APIs, semantic layers, and protocols such as MCP
Make AI systems production-grade
- Write evaluation suites and regression tests for LLM-powered features, and monitor cost, latency, and quality in production
- Apply solid engineering practices: version control, code review, automated testing, CI/CD, and observability
- Deploy on cloud infrastructure (GCP, Azure, or AWS) using containers, serverless, and infrastructure-as-code
- Build and maintain the data pipelines that feed AI systems, across warehouses, lakehouses, and vector stores
Work AI-natively and client-facing
- Use agentic coding tools (Claude Code, Gemini CLI, Codex, Cursor) daily, with good judgment about verification and review
- Communicate progress, trade-offs, and blockers clearly to clients and project leads
- Support pre-sales when needed: scope solutions, build demos, and estimate effort alongside partnership and consulting teams
- Mentor junior engineers and contribute to internal accelerators, reusable components, and engineering standards
Requirements & Qualifications
- 3–5 years of experience in software engineering or data engineering, with extensive hands-on use of AI tools and LLM-based development over the past year (professional projects, internal initiatives, or substantial personal builds)
- Experience with front-end development (React or similar) and at least one backend framework
- Hands-on experience with RAG, embeddings, and vector search, and with at least one agentic framework (LangGraph/LangChain, Google ADK, Claude Agent SDK, or OpenAI Agents SDK)
- Specialization in at least one major AI platform ecosystem — Google (Gemini, Vertex AI, Gemini Enterprise), Anthropic (Claude, Managed Agents, MCP), or OpenAI (Responses API, AgentKit) — and working experience with one cloud platform (GCP, Azure, or AWS)
- Fluency with agentic coding tools such as Claude Code, Gemini CLI, Codex, or Cursor
- Experience building and maintaining data pipelines
- Professional English proficiency (C1/C2 minimum), mandatory: the role involves daily work with international clients and colleagues
- Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field, or equivalent practical experience
Certifications
A certification on at least one major AI platform or cloud is a strong differentiator. Candidates who do not hold one yet are expected to obtain one within the first 2 months in the role, and the client sponsors the exam and provides preparation time. Examples include Claude Certified Developer – Foundations, Google Cloud Professional Machine Learning Engineer, Google Cloud Generative AI Leader, Microsoft Azure AI Engineer Associate, or equivalent AWS credentials.
Nice to Have
- Experience with MCP servers, multi-agent patterns, or LLM evaluation tooling (LangSmith, Langfuse, promptfoo)
- Experience with Terraform or CI/CD pipelines
Key Capabilities
- Breadth across the full stack, with depth in at least one AI platform
- Owns features end to end, from interface to infrastructure
- Cares about evaluation and reliability, not just the happy path
- Communicates clearly with clients in demos, documents, and code review
- Client-facing mindset: understands client needs and translates business requirements into technical solutions
- Learns new tools and models fast, and shares what works
- Flexible work setup, with the option to work from home or anywhere you prefer
- Life, health, and dental insurance
- Regular in-person team gatherings, with workshops, lectures, training, and social activities
- Access to coworking spaces
- Semi-annual performance evaluations, with opportunities for promotion