Staff AI Engineer
New
F
FactoredArtificial Intelligence
Location: Latin AmericaFull-TimeStaff
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Languages
- Fluent English
- Experience
- 8+ years of experience in Software/ML Engineering, with 3+ years specifically focused on production GenAI/LLM applications and 2+ years in customer-facing or forward-deployed roles.
- Required Skills
- AWSDockerPythonKubernetesTerraformGenerative AILangChain
Requirements
- 8+ years of experience in Software/ML Engineering.
- 3+ years specifically focused on production GenAI/LLM applications (RAG, agents, tool use).
- 2+ years in customer-facing or forward-deployed roles.
- Deep hands-on experience with Generative AI frameworks such as LangGraph, LangChain, LlamaIndex, OpenAI, and vector databases.
- Proven ability to architect and scale complex backend microservices and APIs using Python.
- Hands-on expertise building, deploying, and managing cloud-native applications on AWS, GCP, Azure, or Databricks.
- Proficiency with Docker, Kubernetes, Terraform, MLflow, and automated CI/CD pipelines.
- Experience implementing LLM telemetry, cost-tracking, security guardrails, and systematic evaluation harnesses.
- Exceptional ability to structure ambiguous client problems into clear technical requirements.
- Fluent English communication (written and spoken).
Responsibilities
- Partner with client executives to translate ambiguous business problems into enterprise AI solution architectures with clear trade-off analyses.
- Design and build scalable backend systems, data pipelines, and APIs integrating LLMs, agentic workflows, and RAGs.
- Implement multi-agent orchestration frameworks and advanced retrieval mechanisms for complex workflows.
- Deploy and manage cloud-native AI applications across AWS, GCP, Azure, or Databricks using Docker, Kubernetes, Terraform, and CI/CD pipelines.
- Instrument systems with LLM telemetry, cost-tracking, security guardrails, and systematic evaluation harnesses to ensure safety and performance.
- Fine-tune prompts and optimize inference latency using caching, quantization, and cost-reduction strategies.
- Serve as the embedded technical authority within client environments to align cross-functional teams and manage technical risks.
- Elevate team standards and mentor client technical staff to build long-term operational autonomy.
View Full Description & ApplyYou'll be redirected to the employer's site
