Senior AI Engineer - Conversational AI Lead (Remote)

Talent Inc.; United States; Remote; USD 150,000 - 230,000; Full time

Job summary

Careerminds is building an AI career companion app, a 100% remote product with a conversational assistant that can update resumes, search for jobs, prepare for interviews, and track outcomes. You will own core ML/AI decisions in a small team, shaping technical directions and tool choices.

The role emphasizes shipping LLm-based features to real users, with responsibilities spanning memory, agent orchestration, evaluation, safety, and production integration using FastAPI, Postgres, Redis, and AWS.

Qualifications

• 5+ years as a software or ML engineer, including shipping LLm-based products to real users.
• Experience building a conversational product with measurable outcomes.
• Production experience with agent frameworks (LangGraph or similar), tool calling, MCP, structured outputs, state management.
• Experience evaluating multi-turn systems: offline eval sets, judge validation, online testing.
• Experience with guardrails and adversarial input in a live product.
• Experience with streaming, latency, and cost optimization for LLM systems.
• Proficient in Python, asynchronous programming, and API design; familiar with Git, Docker, and AWS.

Responsibilities

• Design and own the core conversational product, including memory and agent orchestration.
• Implement multi-step workflows with explicit state, tool calls, and agent handoffs.
• Coordinate model providers based on cost, latency, and quality, with robust fallbacks.
• Create traces for every decision to enable debugging and improvement.
• Ensure safety, guardrails, and compliance across the product.

Skills

Python

Asynchronous programming

API design

Git

Docker

AWS

Tools

LangGraph

MCP

PostgreSQL

Redis

FastAPI

Job description

Careerminds is building an AI career companion app, a 100% remote product with a conversational assistant that can update resumes, search for jobs, prepare for interviews, and track outcomes. You will own core ML/AI decisions in a small team, shaping technical directions and tool choices.

The role emphasizes shipping LLm-based features to real users, with responsibilities spanning memory, agent orchestration, evaluation, safety, and production integration using FastAPI, Postgres, Redis, and AWS.