AI Engineer

Insight Softmax Consulting LLC; Oregon; Hybrid; USD 140,000 - 220,000; Full time

Benefits offered by this job

Remote work environment

Job summary

Insight Softmax is hiring an AI Engineer to implement AI platforms and services including inference stacks, AI gateways, RAG and agent systems.

You will work inside customer environments, from neoclouds with GPUs to enterprises deploying production LLM services, and contribute to our platform products for vendor partners.

Qualifications

• At least 4 years software or platform engineering experience with 2+ years building ML/LLM services in production.
• Hands-on with at least one inference server (vLLM, TensorRT-LLM, Triton, llm-d) and GPU workloads on Kubernetes.
• Strong Python, ability to build services, CLIs and automation with tests.

Responsibilities

• Deploy and operate LLM inference services on Kubernetes and GPU clusters with autoscaling and tuning.
• Build AI gateway and routing layers: tenants, quotas, rate limits, caching, metrics.
• Implement RAG pipelines, agent workflows, and APIs for customer applications.
• Write production-quality Python services and IaC for the platform.
• Instrument services for observability: latency, throughput, costs.

Skills

Python

Kubernetes

Linux

LLM/ML services

Cloud platforms

Tools

vLLM

TensorRT-LLM

Triton

llm-d

Job description

Insight Softmax is a leading organization in the fields of machine learning, data science, and high-performance computing (HPC). We are dedicated to providing innovative solutions in computing technology to solve complex problems in various sectors including research, science, manufacturing, finance, and data analytics.

Description

We are hiring an AI Engineer for our engineering team. You will implement the AI platforms and services our architects design and our customers run: inference stacks, AI gateways, RAG and agent systems, and the automation around them.

You will work directly inside customer environments, from neoclouds with thousands of GPUs to enterprises deploying their first production LLM service, and on our own platform product work for vendor partners.

The role is forward-deployed in spirit. You will spend much of your work embedded with a customer team, shipping working systems and leaving behind documentation and automation they can run.

Our team requires individuals with focus on delivery and results, hunger to learn, ability to adapt, and can thrive in a self-directed environment where you'll figure out what's needed to deliver rather than wait for detailed instructions.

Key Responsibilities

• Deploy and operate LLM inference services on Kubernetes and bare metal GPU clusters, including model serving, autoscaling, GPU scheduling and performance tuning.
• Build and operate AI gateway and routing layers: tenant keys, model pools, quotas, rate limits, caching, failover and usage metrics.
• Implement RAG pipelines, agentic workflows, evaluation harnesses and the APIs that expose them to customer applications.
• Write production-quality services and automation in Python, with infrastructure as code for the surrounding platform.
• Instrument AI services for observability: latency, throughput, token and cost accounting, quality signals.
• Run benchmarks and load tests, and turn results into tuning changes and capacity recommendations.
• Integrate AI services with customer identity, security and data systems.
• Document deployments and hand over runbooks to customer and internal operations teams.
• Reserve time each week for pre-sales support, internal platform work and knowledge sharing.

Qualifications

• At least 4 years of software or platform engineering experience, with at least 2 years building and running LLM or ML services in production.
• Hands-on with at least one inference server (for example vLLM, TensorRT-LLM, Triton, llm-d) and with running GPU workloads on Kubernetes.
• Strong Python. Comfortable building services, CLIs and automation, with tests.
• Working knowledge of Kubernetes, containers, Helm and GitOps workflows.
• Strong linux chops.
• Deep knowledge of at least one of AWS, GCP, or Azure. Preferably AWS.
• Experience with LLM application patterns: prompt and context management, retrieval, tool use, structured output, evaluation.
• Able to work independently inside a customer environment and communicate progress clearly.

Optional Experience and Skills

• AI gateway tooling (for example LiteLLM, Envoy or Traefik based gateways, KubernetesGateway API inference extensions).
• Vector databases and embedding pipelines.
• Fine-tuning, quantization and model optimization.
• Multi-tenant GPU platforms, GPU partitioning and Dynamic Resource Allocation.
• Observability stacks (OpenTelemetry, Prometheus, Grafana, Datadog) applied to AI services.
• Spectro Cloud Palette and PaletteAI, Run:ai, or similar GPU platform products.
• Slurm or other batch schedulers.

Bonus Experience and Skills

• Go or Rust.
• Terraform and Ansible.
• Air-gapped or regulated environment deployments.
• Using linux as your primary desktop workstation environment.

Attributes that we value

• Transparency
• Grit
• Effectiveness
• Willingness to learn

Location and Hours

• Full time position
• Remote work environment
• 80% of your work schedule will be during the business time zones for Latin America and Canada.
• Some customer meetings will occur each week at non-standard / nighttime hours, as wecurrently support a global team across 3-4 continents.
• Some customer engagements include on-site work at US customer sites, typically forworkshops, platform bring-up and go-live. Expect occasional US travel.

References

• 3 references will be required.

Notes

• AI systems may be used with the recruitment and screening processes for this job requisition.