Software Engineer, AI Platform

San Francisco. Posted 6 months ago

The role

This person will own the data platform, ETL pipelines, and agent infrastructure. They will build the platform layer that makes AI work reliable, observable, and usable in production.

What you will do

Own the data platform
Run the LLM ETL pipeline
Build agent transformation infrastructure
Improve reliability, throughput, and cost of LLM-driven jobs in production
Build observability and tooling
Partner with AI Engineers
Operate the system and participate in on-call rotation and incident response

Required qualifications

Strong Python engineering experience supporting production systems (FastAPI or similar)
Experience building or maintaining production pipelines that handle non-trivial volume, retries, backfills, and failure recovery
Hands-on experience with a data orchestrator (Dagster, Airflow, Prefect, or Temporal) and dbt or similar transformation tooling
Comfort with PostgreSQL at scale: schema design, multi-schema setups, and migrations
Comfort with AWS infrastructure (ECS, Lambda, SQS, Step Functions, RDS, S3) and IaC (Terraform / Terragrunt)
Familiarity with LLM APIs and the operational realities of LLM-based systems (latency, cost, retries, structured output, failure modes)

Nice to have

Experience with distributed compute for Python workloads: Anyscale Ray, Dask, or Spark
Experience with Polars and Pandas for data processing
Familiarity with Datadog for observability, metrics, and tracing
Cost optimization experience for LLM workloads
Familiarity with pgvector or other vector stores
Multi-region AWS deployment experience
Some TypeScript/Node experience

Benefits

ESOP
US$1,000 per month food and commuting allowance
Laptop of choice

Before you apply

E-3 sponsorship is offered for Australians to relocate with stipend
Hiring process includes resume screen, 1:1 with founder, technical deep-dive, and working through a real problem with the team

About the company

Fluency builds a platform that captures how work actually happens inside large organizations, measures productivity and process conformance, and analyzes where AI can do the work.