Staff AI Engineer

Velocity Talent; United States; Remote; USD 207,000 - 253,000; Full time

Job summary

Velocity Talent is hiring a Staff AI Engineer for Robots & Pencils to build and ship AI coworkers into enterprise systems. This senior backend role focuses on production-grade AI platforms in a mature environment, with remote US work and travel.

Requires 6+ years of software engineering, strong Python/Node.js, and hands-on LLM tool calling with multi-agent orchestration on AWS. Expect ownership of features end-to-end and mentoring opportunities.

Qualifications

• 6+ years of professional software engineering experience.
• Strong Python and Node.js proficiency.
• Hands on experience with LLM tool calling and multi-agent orchestration.
• AWS services exposure across Lambda, DynamoDB, S3, SQS, EventBridge and Step Functions.
• API design, backend development, and testing strategy.

Responsibilities

• Build and maintain backend services and APIs in Python and Node.js.
• Engineer production AI features: LLM function calls, multi-agent orchestration, vector search, RAG and streaming responses.
• Design AWS native serverless systems with Lambda, DynamoDB single-table design, S3, SQS, EventBridge and Step Functions.
• Support workflow orchestration and event-driven processes; contribute to full-stack integration.
• Improve reliability, troubleshoot production systems, and assist with releases.
• Review code, mentor engineers, and own features end to end.

Skills

Python

Node.js

LLM tool calling

Prompt engineering

Multi-agent orchestration

Embeddings

Vector databases

Streaming responses

RAG

Tools

AWS Lambda

DynamoDB

S3

SQS

EventBridge

Step Functions

OpenSearch

Job description

Velocity Talent is hiring a Staff AI Engineer for Robots & Pencils, an applied AI engineering firm that builds and ships AI coworkers into enterprise business systems. This is a senior backend and AI platform role in a mature production environment with real enterprise users.

Type: full time, one opening, start ASAP.
Compensation: up to $230,000.
Location: fully remote, US only, with about 20% travel (an in person interview and a one week onboarding, expenses covered).
Work authorization: must be authorized to work in the US without sponsorship.

The one thing we screen for first

You need hands on experience with AWS Bedrock AgentCore, or a multi agent system you actually deployed to AWS: several coordinating agents running on real AWS infrastructure. LangGraph, CrewAI, AutoGen, Strands or a custom framework all count, as long as it shipped to AWS. Single agent chatbots, RAG only projects and notebook work don't meet this bar.

What you'll do

• Build and maintain backend services and APIs in Python and Node.js
• Engineer production AI features: LLM function and tool calling, multi agent orchestration, vector search on OpenSearch, RAG and streaming responses
• Design AWS native serverless systems with Lambda, DynamoDB single table design, S3, SQS, EventBridge and Step Functions
• Support workflow orchestration and event driven processes, and contribute to full stack integration
• Improve reliability, troubleshoot production systems and support releases
• Review code, mentor engineers and own features end to end

What you'll need

• 6+ years of professional software engineering
• Strong Python and Node.js
• Hands on LLM tool calling, prompt engineering, multi agent orchestration, embeddings, vector databases, streaming responses and RAG
• AWS experience across Lambda, DynamoDB, S3, SQS, EventBridge and Step Functions
• API and backend design, SQL and NoSQL databases, Docker, unit testing and sound test strategy

Nice to have

• Langfuse, synthetic AI testing, token cost optimization and reasoning effort tuning
• Step Functions for AI workflows