Senior Artificial Intelligence/Machine Learning Engineer

Ciklum is looking for a Senior Artificial Intelligence/Machine Learning Engineer to join our team in Brazil.

We are a custom product engineering company that supports both multinational organizations and scaling startups to solve their most complex business challenges. With a global team of over 4,000 highly skilled developers, consultants, analysts and product owners, we engineer technology that redefines industries and shapes the way people live.

About the role:

As a Senior Artificial Intelligence/Machine Learning Engineer, you'll become a part of a cross-functional development team engineering experience of tomorrow.

Responsibilities:

Agent Development: Design, build, and test production-grade agents (e.g., Lease Abstraction, CAM Reconciliation) using the Prodigy framework as a baseline

SDK & Gateway Engineering: Develop a lightweight Python SDK to interface between agents and the platform Control Plane, abstracting complex LLM routing to providers like AWS Bedrock and Anthropic

Knowledge Engineering: Build and configure RAG (Retrieval-Augmented Generation) knowledge bases and GraphDB mappings to provide agents with secure, domain-specific context

Safety & Governance: Implement "Human-in-the-Loop" (HITL) escalation interfaces, confidence thresholds, and strict egress controls to prevent data exfiltration. Ensure all AI solutions comply with security, data privacy, and responsible-AI standards

Optimization: Configure "Agent Overrides" and token optimization strategies (e.g., "balanced" vs. "perfectionist" consumption) via configurable workflows

End-to-End Development: Lead the design, development, and deployment of advanced AI systems across Data Science and AI Engineering domains Contribute hands-on to development activities, from experimentation and prototyping to production-grade implementation

Architecture & Pipelines: Architect and implement scalable AI pipelines and LLM-driven applications, including RAG, orchestration, and multi-agent systems

MLOps / LLMOps: Apply MLOps and LLMOps best practices for CI/CD, observability, evaluation, and continuous improvement of AI models and pipelines

Ecosystem Integration: Integrate AI services with enterprise platforms (e.g., Confluence, Jira, GitHub, CRM, ERP) and ensure seamless interoperability

Cross-Functional Collaboration: Collaborate with cross-functional engineering, data, and product teams to align technical solutions with client and business objectives

Innovation: Drive innovation through internal frameworks and accelerators

Requirements:

AI Ecosystem: Extensive experience with Python, LangChain, and LangSmith; familiarity with the Prodigy framework is a significant advantage

Agentic Intelligence: Proven track record building multi-step reasoning chains, tool-use protocols, and state management for autonomous agents

Data Architecture: Practical experience with Vector Databases (ChromaDB, PGVector) and building ETL "Data Engines" for secure agent consumption via MCP

Infrastructure: Understanding of containerization (Docker/K8s) and isolated runtimes such as Firecracker MicroVMs for agent sandboxing

Integration: Experience integrating AI solutions with enterprise identity providers like WorkOS for multi-tenancy

Workflow Orchestration: Experience with Temporal for managing long-running, multi-stage agentic workflows

Desirable:

Domain Expertise: Familiarity with Commercial Real Estate workflows (Lease accounting, CAM reconciliation)

Evals Literacy: Experience building programmatic "Evaluation Harnesses" and testing against "Golden Datasets" to measure hallucination rates

What’s in it for you?

Care: your mental and physical health is our priority. We ensure comprehensive company-paid medical insurance and mental health programs, 5 undocumented sick-leave days per year

Tailored education path: boost your skills and knowledge with our regular internal events (meetups, conferences, workshops), Udemy license, language courses and company-paid certi