Production AI Engineer — Decision Intelligence

Socket.dev

San Francisco (CA)

On-site

USD 180,000 - 240,000

Full time

14 days+

Get more replies from employers

Send a job-specific resume in minutes.

Job summary

Recourse is building a decision system that improves arbitration outcomes through a blend of deterministic rules and LLM reasoning. You will own the intelligence layer, shaping which claims to contest and what evidence to include. The stack includes TypeScript, Next.js, Prisma, and PostgreSQL on Google Cloud.

You will design and deploy production-grade evaluation, guardrails, and explainability, collaborating across operations, payer strategy, and product to deliver measurable value.

Qualifications

  • 5+ years engineering with meaningful recent time building LLM-powered or ML-driven products in production.
  • Real experience with evaluation: building golden datasets, running offline evals, measuring whether changes helped.
  • Comfort across the stack. You can ship end-to-end, not just the model layer.
  • Strong instincts for where probabilistic reasoning helps and where it introduces risk.
  • Comfort with TypeScript or Python and picking up stack quickly.
  • Experience in regulated or security-sensitive environments is a plus.
  • Preference for small teams and early-stage chaos over mature org charts.

Responsibilities

  • Build the decision engine that determines which claims to contest and at what offer amount.
  • Design the LLM systems that generate arguments: medical necessity, patient acuity, market comparables, the full submission.
  • Build evaluation infrastructure: golden datasets, offline evals, and measuring impact on outcomes.
  • Architect the split between deterministic rules and model reasoning, and defend where you draw the line.
  • Close the feedback loop from arbitration outcomes back into the system to improve future decisions.
  • Build for explainability so every recommendation has reasoning a customer would accept.
  • Partner with operations and payer strategy to surface patterns in claims early.

Skills

LLM systems
Production ML
End-to-end shipping
TypeScript/Python
Regulated environments

Tools

TypeScript
Next.js
Prisma
PostgreSQL
Google Cloud

Job description

Recourse is building a decision system that improves arbitration outcomes through a blend of deterministic rules and LLM reasoning. You will own the intelligence layer, shaping which claims to contest and what evidence to include. The stack includes TypeScript, Next.js, Prisma, and PostgreSQL on Google Cloud.

You will design and deploy production-grade evaluation, guardrails, and explainability, collaborating across operations, payer strategy, and product to deliver measurable value.

Get your free, confidential resume review.
or drag and drop your file here.
Similar jobs

Similar jobs worth comparing

AI Engineer, Decision Intelligence for Arbitration
AI Engineer, Decision Intelligence for Arbitration

landa • San Francisco (CA)

On-site
USD 180,000 - 220,000
AI Engineer, Decision Intelligence
AI Engineer, Decision Intelligence

landa • San Francisco (CA)

On-site
USD 180,000 - 220,000
Claims Platform Engineer — AI-Driven, Production-Ready
Claims Platform Engineer — AI-Driven, Production-Ready

landa • San Francisco (CA)

On-site
USD 140,000 - 180,000
AI Engineer, Decision Intelligence
AI Engineer, Decision Intelligence

Socket.dev • San Francisco (CA)

On-site
USD 180,000 - 240,000
Automated Decisioning Engineer
Automated Decisioning Engineer

Mylitm • California (MO)

On-site
USD 120,000 - 180,000
Staff AI Data Platform Engineer - Real-Time Decisioning
Staff AI Data Platform Engineer - Real-Time Decisioning

Phoenix Technologies, Inc. • United States

On-site
USD 180,000 - 240,000
Automated Decisioning Engineer
Automated Decisioning Engineer

Soledad Data Solutions • California (MO)

On-site
USD 120,000 - 160,000
Low-Latency Decisioning Engineer
Low-Latency Decisioning Engineer

Mylitm • California (MO)

On-site
USD 120,000 - 180,000
Data Scientist
Data Scientist

Compunnel, Inc. • Louisville (KY)

On-site
USD 110,000 - 140,000
Production AI Engineer — LLMs, RAG & Agentic Workflows (Hybrid)
Production AI Engineer — LLMs, RAG & Agentic Workflows (Hybrid)

Nasdaq • Atlanta (GA)

Hybrid
USD 140,000 - 190,000
401(k) match
Employee Stock Purchase Program
Student loan repayment
+2