Data AI Engineer

RV Soft; Chicago (IL); Híbrido; USD 76 000 - 83 000; Tempo integral

Resumo da oferta

RV Soft is seeking a Data AI Engineer to build and operate LLM platform capabilities alongside production data pipelines in a Chicago-based hybrid role.

The position focuses on streaming, observability, and infrastructure guardrails within a regulated enterprise environment, with extensive use of Kafka, Snowflake, and monitoring tools. You will shape data pipelines for audit and consumption use cases while ensuring strong runtime observability.

Qualificações

• Data Engineering: 10 years (Required).
• AI: 2 years (Required).
• Kafka: 10 years (Required).
• OpenTelemetry: 6 years (Required).

Responsabilidades

• Build and operate an API gateway, reverse proxy, or multi-tenant platform.
• Implement LLM delivery features such as streaming and server-sent events, plus token accounting.
• Apply prompt and response guardrails and support model evaluation.
• Use Kafka and Snowflake for audit and consumption data pipelines.
• Deliver strong observability using Prometheus and PromQL, Grafana, Loki, and OpenTelemetry.
• Operate effectively in a regulated enterprise environment with proxies and private networking.

Conhecimentos

Data Engineering

AI

Kafka

OpenTelemetry

Ferramentas

API gateway

Reverse proxy

Multi-tenant platform

Kafka

Snowflake

Prometheus

PromQL

Grafana

Loki

OpenTelemetry

Redis

Valkey

Descrição da oferta de emprego

RV Soft is seeking a Data AI Engineer to help build and operate LLM platform capabilities alongside production data pipelines. This hybrid role in Chicago focuses on regulated, enterprise-grade delivery, with an emphasis on streaming, observability, and infrastructure guardrails.

The work spans API and platform engineering, Kafka and Snowflake pipelines for audit and consumption data, and deep monitoring using industry-standard tooling. The role also requires experience operating components across private networking, corporate proxies, and strict change control.

Role focus

• LLM platform engineering, including streaming and server-sent events
• Token accounting and prompt and response guardrails
• Model evaluation as part of production readiness
• Design and operation of data pipelines supporting audit and consumption use cases

Responsibilities

• Build and operate an API gateway, reverse proxy, or multi-tenant platform
• Implement LLM delivery features such as streaming and server-sent events, plus token accounting
• Apply prompt and response guardrails and support model evaluation
• Use Kafka and Snowflake for audit and consumption data pipelines
• Deliver strong observability using Prometheus and PromQL, Grafana, Loki, and OpenTelemetry
• Use Redis or Valkey beyond basic caching, including counters and TTLs and distributed rate-limiter semantics
• Operate effectively in a regulated enterprise environment with corporate proxies, private networking, and strict change control

Required experience

• Data Engineering: 10 years (Required)
• AI: 2 years (Required)
• Kafka: 10 years (Required)
• OpenTelemetry: 6 years (Required)

Key technologies

• API gateway, reverse proxy, multi-tenant platform
• Server-sent events
• Token accounting
• Kafka, Snowflake
• Prometheus, PromQL, Grafana, Loki, OpenTelemetry
• Redis, Valkey

Compensation and logistics

• Pay: USD $55.00 - $60.00 per hour
• Expected hours: 40.0 per week
• Work location: Hybrid remote in Chicago, IL 60616