About this role
Why join us
AI Engineering at Tractian
What you'll do
Responsibilities
- Design and develop production-grade applications and custom agentic workflows powered by LLMs.
- Build intelligent data processing workflows using OCR, PDF layout analysis, audio and image models.
- Architect and scale event-driven data streaming pipelines using Apache Kafka to power AI workloads.
- Create and maintain high-performance APIs that integrate AI capabilities with our platform.
- Implement evaluation frameworks (evals) to benchmark and track model quality, accuracy, and regressions.
- Partner proactively with product teams to define technical requirements.
- Mentor engineers, drive architecture discussions, and ensure best practices through code reviews.
Requirements
- 5+ years of experience in software engineering with a strong backend/distributed systems foundation.
- 2+ years of experience building and shipping production AI/LLM systems.
- Bachelor's degree in Computer Science, Engineering, Information Systems, or equivalent technical field.
- Demonstrated experience building production-grade applications with custom agentic systems, document processing pipelines, and/or information-retrieval systems.
- Hands-on experience with event-driven architectures and streaming using Apache Kafka.
- Working knowledge of AI evaluation methods (evals), observability/tracing, security guardrails, cost optimization, latency reduction, and semantic caching.
- Strong proficiency in Python and/or Golang, with experience in frameworks like FastAPI or Flask.
- Strong proficiency in designing, building, and maintaining production REST APIs and databases.
- High ownership and strong product sense: able to take ambiguous problems, collect technical requirements, prioritize impact, and execute independently.
Preferred Qualifications
- Experience with LLM fine-tuning and model optimization techniques.
- Knowledge of containerization (Docker, Kubernetes) and microservices architecture.
Technical Skills
- Programming: Python and/or Golang.
- Frameworks: FastAPI, Flask.
- Agentic Systems: Custom state machines, tool-calling pipelines, execution loops.
- Streaming & Messaging: Apache Kafka, event-driven architecture.
- Document Processing: OCR engines, PDF parsing, multimodal LLMs.
- AI Reliability: Evals (LLM-as-a-judge, benchmarks), observability, tracing, guardrails.
- API Development: REST, OpenAPI, gRPC.
- Databases: PostgreSQL, Redis, vector databases.
- LLM Integration: OpenAI, Anthropic, and open-source models.
Compensation & Benefits
- Competitive Compensation
- 30 days of paid annual leave
- Education and courses stipend
- Earn a trip anywhere in the world every 4 years
- R$1.035/month for meals allowance
- Health plan with national coverage and without coparticipation
- Dental Insurance: we help you with dental treatment for a better quality of life.
- Wellhub Membership: Access a wide range of gyms and training programs.
Apply to Tractian
Clera fills in Tractian's application for you.
How it works
Open the role in Clera
Sign in, and this role opens on your Clera job board, ready to apply.
Clera fills in the application
Clera fills the form from your profile and resume, and asks what's missing.
Track it in Clera
Each application you send shows up in your Clera tracker, sorted by stage.
Ask your AI about this role
It knows you. Clera gives it the role.
First time? Connect Clera once, about a minute.
https://mcp.getclera.comSign in with your Clera account. MCP docs
About Tractian
TRACTIAN reimagines industrial systems so that every frontline maintenance worker can realize their full potential. The company builds software and hardware in one place, delivering integrated solutions for industrial operations. TRACTIAN disrupts long-standing institutions with products and experiences that better serve the ambitions of its clients. As a growth-stage startup, it emphasizes rapid development and market impact. The company states that employees will work directly with the founders to help define the vision, product, and user experience.
- Team size
- 501-1000 people
- Founded
- 2019
- Industry
- Hardware
- Workplace
- On-site
- Locations
- São Paulo, São Paulo, Brazil