Senior Software Engineer (Tysons Corner)

Senior Software Engineer – LLM Reliability

About the Company

Pam is the fastest-growing voice AI platform for auto dealerships. We handle millions of calls, book service appointments, and drive real revenue for 500+ dealerships. To do this, we integrate with every major Dealer Management System — Tekion, CDK, XTime, MyKaarma, Dealer-FX, and more.

We're hiring a Senior Engineer to own LLM reliability. This isn't a feature role. This is the make it bulletproof role. You'll be the person who ensures Pam says the right thing, every time, and catches problems before customers do.

If you get energy from making AI systems reliable at scale—not just shipping demos—this is your role.

Pam.ai is not able to provide employment visa sponsorship at this time. Candidates must be authorized to work in the United States without current or future sponsorship.

Role

• Own LLM reliability and response quality across our voice AI platform

• Build observability into LLM behavior—know when Pam is performing well vs struggling

• Reduce hallucinations, failed intents, and bad responses through better prompts, model selection, and fallback strategies

• Create customer health monitoring so we catch issues before they become complaints

• Ship fast—we expect code in production your first week, and meaningful impact within your first month

• Mentor junior engineers on LLM reliability practices

Qualifications

• Have 5+ years of software engineering experience, with at least 1 year working on production LLM systems

• Are strong in TypeScript (our entire stack) and AWS

• Use AI to code — Claude Code, Cursor, Copilot, or equivalent. This is how we work.

• Know how to improve a live system without breaking it

• Have opinions on how to make LLMs reliable, not just how to use them

• Think in terms of measuring and improving, not just shipping and hoping

• Can debug deeply when an LLM is behaving badly—prompt issues, context problems, model limitations

• Move fast but care about quality—you ship Day 1, but you think about what could go wrong

• Get energy from reliability work, not just feature work

Preferences

• Experience with voice AI, conversational systems, or real-time AI

• Built LLM evaluation frameworks or quality monitoring systems

• Context engineering: structuring prompts and systems so they're observable and debuggable

• Background in reliability engineering, SRE, or production ML systems

• You've been on-call for AI systems and have scars to show for it