About Trantor:

Trantor is a technology services company focused on outsourced product development and digital re-engineering. Leveraging our CaptiveCoE™ engagement model, we operate as a seamless extension of our client’s teams to provide rapid scalability with predictable budgets. Founded in 2012, Trantor has worked with customers across Tech, FinTech, Media & Cybersecurity industries. We have centers in the US, India, Canada, and Costa Rica. We are consistently rated as the #1 employer in the region with the ability to attract and retain technical talent. Our commitment to excellence and impactful results has translated to long-term relationships and value for our clients and solution partners. 

Job Overview

We are seeking an AI/ML Engineer to design, build, and scale intelligent AI-driven systems using Python, RESTful APIs, and AWS AI/ML services. This role requires strong expertise in LLMs, agentic workflows, and document extraction systems, along with the ability to make informed architectural decisions by evaluating trade-offs across performance, cost, accuracy, and scalability.

The ideal candidate is hands-on, technically deep, and capable of guiding design discussions, reviewing complex codebases, and mentoring engineers while delivering production-grade AI solutions.

Key Responsibilities

• Design and develop scalable, high-performance Python services
• Build and maintain REST APIs using Python
• Implement async processing for I/O-heavy and compute-intensive workloads
• Design and implement LLM-based and agentic workflows using AWS AI services (such as Amazon Bedrock and SageMaker)
• Architect document and data extraction pipelines for structured and unstructured inputs (PDFs and other formats)
• Evaluate and clearly communicate technical trade-offs and architectural decisions
• Debug, optimize, and harden systems for production environments
• Review and refactor complex Python codebases, ensuring maintainability and type safety
• Collaborate with cross-functional teams to translate business needs into scalable technical solutions

• Strong hands-on Python development with production-grade coding practices
• Experience building and maintaining APIs using python
• Ability to write scalable async code using asyncio / async I/O patterns
• Strong focus on type safety using typing and Pydantic (or equivalent)
• Ability to read, understand, and refactor complex Python codebases
• Hands-on exposure to AWS AI/ML services such as Amazon Bedrock, SageMaker, or AWS AI Builder tools
• Experience with Amazon Textract or similar document AI services
• Deep understanding of LLMs (context limits, latency, cost, hallucinations, evaluation)
• Experience creating agents and agentic workflows (tool-calling, orchestration, multi-step flows)
• Strong experience designing document extraction systems (PDFs and other unstructured formats → structured output)
• Understanding of PDF extraction approaches and limitations (scanned vs digital, tables, layouts, OCR constraints)
• Strong ability to discuss and justify trade-offs (accuracy vs latency, cost vs capability, OCR vs LLM, etc.)
• Strong debugging and performance optimization skills across Python and ML/LLM stacks
• Familiarity with logging, monitoring, and troubleshooting production issues in service-based systems on AWS

• Experience with multi-agent architectures
• Exposure to evaluation frameworks for LLM outputs
• Knowledge of cost optimization strategies for AI systems
• Familiarity with cloud-native architectures on AWS
• Experience working with large, enterprise-scale document workflows