Senior Software Engineer, Applied AI
Build and own production AI agent systems spanning orchestration, backend services, integrations, knowledge infrastructure, trust and safety, and evaluation. The role requires 5+ years of backend engineering experience, hands-on LLM or agent experience, and strong ownership in an ambiguous product environment.
About the job
Responsibilities
- Design, build, and own core components of the agent platform, including the orchestration layer and tool integrations with internal systems.
- Build and evolve the capabilities layer, including APIs, data access patterns, and service integrations for agents to execute operational workflows.
- Architect knowledge and memory infrastructure that enables agents to retrieve data and act across systems.
- Design and implement trust and safety frameworks, including audit trails, human-in-the-loop controls, and guardrails for safe, auditable AI-driven operations.
- Contribute to agent evaluation and testing infrastructure, defining measures for accuracy, reliability, and regression across agent behaviors.
- Partner with Operations to understand workflows, identify automation opportunities, and translate process knowledge into agent capabilities.
- Mentor other engineers as the team grows.
Requirements
- 5+ years of backend engineering experience building and operating production systems.
- Hands-on experience with LLMs and AI agents, including orchestration, retrieval-augmented generation (RAG), tool/function calling, or similar.
- Strong API design and system integration skills.
- Product-minded approach, including questioning requirements and contributing to product decisions.
- Proven ownership of complex projects in ambiguous, early-stage environments.
- Strong backend engineering fundamentals and ability to design, build, and operate production systems.
- Curiosity and motivation to build practical products using AI and LLMs, particularly agent systems.
Technologies
- Golang
- Ruby on Rails
- JavaScript
- Java
- C#
- Python
- VueJS
- MySQL
- Kafka
- AWS
- Git
- Memcache
- Redis
- Elasticsearch
- Docker
- Terraform
- Kubernetes
- CircleCI
- Datadog
Compensation and Benefits
- Base wage range for the Mexico City office: 140,000–180,700 MXN per month.
- Actual compensation depends on factors including skill set, relevant experience, and specific work location.
- Salary ranges for positions in other locations may differ based on local labor costs.
- Benefits are provided under Justworks' Total Reward Philosophy.
Skills
Go, Ruby on Rails, JavaScript, Java, C#, Python, Vue, MySQL, Kafka, AWS, Redis, Elasticsearch, Docker, Terraform, Kubernetes
Similar jobs
ML Engineering jobs
Rollstack
United StatesBuild production AI capabilities for automated slide and document generation, working across LLM applications, data analysis, and content generation. The role requires 3+ years in machine learning and NLP, advanced Python, and experience with LLM frameworks and production systems.
Payabli
Remote
Sets the technical direction for production machine learning across a payments platform, building and scaling models for risk, authorization, disputes, and forecasting. Requires 8+ years of ML engineering experience, including production model ownership and strong technical leadership.
Protege
Remote
Build the technical foundation for a new business vertical, creating reusable infrastructure and leading early customer engagements from scoping through delivery. The role requires 3+ years of engineering experience, strong Python and SQL skills, backend/data expertise, and comfort operating in ambiguity.
Adaption Labs
San Francisco, CA
Build production agent systems that plan, use tools, recover from failures, and improve over time. The role requires 5+ years of production ML or backend experience, LLM or agent deployment experience, and expertise in evaluation, tracing, observability, and agent architecture.
Adaption Labs
San Francisco, CA
Own inference-stack cost and performance by optimizing serving, caching, batching, quantization, decoding, routing, and GPU execution. The role requires 5+ years in ML systems, inference infrastructure, or performance engineering, plus strong Python and systems-language skills.