Senior AI Platform Engineer

Code Metal, Inc.; United States; Híbrido; USD 150 000 - 190 000; Tempo integral

Vantagens oferecidas por esta oferta de emprego

Health care plan (Medical, Dental &amp

401k/IRA Retirement plan

Flexible hybrid work arrangement

PTO (Uncapped Vacation, Sick & Hol

Relocation assistance

Resumo da oferta

Code Metal, Inc. is seeking an Senior Software Engineer for the AI Platform team to design, build, and operate production-grade AI enablement stack components.

You will own platform areas end to end, from design documentation to production operation, and contribute across the stack with a focus on reliability and performance. The role emphasizes model serving, agentic infrastructure, and observability with experimentation.

Qualificações

• Typically 4+ years of software engineering experience, including 2+ years building and operating ML/AI or LLM systems in production.
• Experience owning a service or component in production, including debugging and reliability improvements.
• Production-grade Python and platform engineering fundamentals: API design, distributed systems, containers and orchestration (Kubernetes), CI/CD, testing.
• Familiarity with inference optimization techniques and GPU profiling.
• Experience deploying AI systems on-prem or in regulated domains such as defense or aerospace.

Responsabilidades

• Own 1 or more platform components end to end, from design to production operation.
• Build and operate the services in your focus area, and contribute across the rest of the stack.
• Review teammates’ code and designs, and help onboard new engineers.
• Run focused benchmarks and experiments when a platform decision needs evidence.
• Debug production issues such as tail latency, GPU memory pressure, or agent runs that fail or loop.

Conhecimentos

Model serving

Observability & experimentation

Production-grade Python

Agentic infrastructure

LLM systems in production

GPU memory management

Ferramentas

PyTorch

Hugging Face

Kubernetes

MLflow

Weights & Biases

TensorRT

Descrição da oferta de emprego

• Code Metal’s engineering teams are building AI-driven code transpilation, modernization, optimization, modeling and simulation solutions
• They all need the same foundations: models to serve, agents to run, context to manage, and results to measure. Our AI Platform team builds those foundations
• As a Senior Software Engineer on the AI Platform team, you’ll design, build, and operate parts of the AI enablement stack our engineers depend on: GPU inference serving, model gateways, agent harnesses, context engineering, observability, and AI experimentation management. It is an internal platform, but we’re building it to product standard
• Over time you will own 1 area, such as model serving, agentic infrastructure, or experimentation and telemetry, while you also contribute across the rest of the stack
• This is an engineering role first. Most of your time goes to designing, building, and operating production systems
• Own 1 or more platform components end to end, from design doc to production operation
• Build and operate the services in your focus area, and contribute across the rest of the stack
• Write clean, well-tested code, and hold AI-generated code to the same bar: correct, modular, and fully tested
• Debug hard production issues in the components you own, such as tail latency, GPU memory pressure, or agent runs that fail or loop
• Scope and estimate efforts with internal customers, and raise risks early
• Review teammates’ code and designs, and help onboard new engineers
• Run focused benchmarks and experiments when a platform decision needs evidence

Benefits

• Health Care Plan (Medical, Dental & Vision)
• Retirement Plan (401k, IRA)
• Flexible hybrid work arrangement
• Paid Time Off (Uncapped Vacation, plus Sick & Public Holidays)
• Relocation assistance for qualifying employees

We don’t expect you to arrive with every skill on this pageYou’ll also need solid data science and AI research fundamentals: you’ll work closely with our Applied AI Research team, and you’ll sometimes run experiments when a platform decision needs evidence

• Agentic infrastructure: Build agent harnesses, orchestration primitives, and context-engineering services (memory, retrieval, and data discovery) that product teams compose into reliable, verifiable workflows
• Observability and experimentation: Instrument the stack end to end, for example, with OpenTelemetry traces and service metrics. Build evaluation harnesses and the experiment-tracking and artifact layer that lets engineers and researchers reproduce and compare results
• Model serving: Deploy, benchmark, and tune elastic, production inference for open-weight models on runtimes such as vLLM, SGLang, and TensorRT-LLM. Run the model gateways that teams use to reach self-hosted and commercial models

Each engineer on the team brings depth in at least 1 of these areas:

• Model serving: deploying and tuning LLM inference, or running an LLM gateway or API gateway
• Observability and experimentation: instrumenting and operating services against SLOs, or building evaluation and experiment-tracking systems
• Experience owning a service or component in production, including debugging and improving its reliability
• Production-grade Python and solid platform engineering fundamentals: API and service design, distributed systems, containers and orchestration (such as Kubernetes), CI/CD, and testing
• Agentic infrastructure: shipping agentic systems, or building context-engineering services such as retrieval-augmented generation, embeddings, and vector or hybrid search
• Solid data science and AI research fundamentals: how transformers and LLM inference work, experiment design, benchmarking, and model evaluation. Working familiarity with PyTorch and Hugging Face

Production experience in at least 1 focus area:Experience writing design docs for focused projects, reviewing code, and mentoring or onboarding teammatesTypically 4+ years of software engineering experience, including 2+ years building and operating ML/AI or LLM systems in productionExperience in more than 1 focus areaProduction experience running an LLM gateway or proxy such as SMG or Bifrost, or building an API gateway, including routing, auth, rate limiting, quotas, failover, and cost attributionFamiliarity with inference optimization: speculative decoding, prefix caching, tensor/pipeline/expert parallelism, GPU profilingExperience with durable workflows, agent frameworks, or tool protocols such as MCPExperience fine-tuning language models, including distributed training across multiple GPU nodesExperience with experiment-tracking or artifact management systems such as MLflow or Weights & BiasesExperience deploying AI systems on-prem or in regulated domains such as defense or aerospace