Skip to content
AlephAleph

Staff+ Software Engineer, AI

Own the shared AI foundation powering Aleph’s financial planning products, including model routing, context and tool systems, evaluations, and observability. The role requires Staff-level experience shipping production LLM and agentic systems, strong technical judgment, and a pragmatic builder’s mindset.

About the job

Responsibilities

  • Own the AI foundation used by product teams, including model selection and routing, the model proxy layer, context management, and tool design.
  • Build and maintain evaluation infrastructure; collaborate with customers and finance-domain experts to define quality standards and encode them in reusable evaluations.
  • Ship agentic features end to end, from initial proof of concept through optimization, including prompt and context engineering, caching, parallel tool calls, and subagent patterns.
  • Build observability into agent behavior to profile performance, identify bottlenecks, and prioritize improvements using data.
  • Track developments in agentic systems and incorporate proven practices into engineering processes.
  • Drive adoption of systems across teams without direct management.
  • Trace requests across the full stack and make sound technical decisions at every layer.

Requirements

  • Production experience shipping LLM systems, including evaluations, context management, and multi-model or multi-provider routing.
  • Experience with LLM APIs, agent frameworks, and user-facing products.
  • Ability to build proofs of concept, make fast decisions, and ship incremental first versions.
  • Strong judgment in designing pragmatic, opinionated abstractions.
  • Strong software engineering fundamentals and code-quality standards.
  • High agency and a builder’s mindset, ideally from founding, engineering leadership, or startup-building experience.
  • Clear, direct, and persuasive communication with technical and non-technical audiences.
  • Experience building complex B2B products, ideally from scratch.
  • Preference for shipping production systems rather than conducting research.

Skills

LLMs, LLM APIs, Agent Frameworks, Model Routing, Context Management, Evaluation Infrastructure, Prompt Engineering, Tool Design, Caching, Parallel Tool Calls, Observability, Subagents, B2B Software

Grafana Labs

Grafana Labs

United States
Staff AI Engineer
CA$164k+/yrRemote8+ YOEML Engineering

Builds and owns production multi-agent AI infrastructure, backend integrations, and workflow automation for marketing operations. Requires 8+ years of software engineering experience, strong Python and JavaScript/Node.js skills, production LLM experience, and deep Google Cloud expertise.

OnePay

OnePay

United States

Staff Applied Scientist, Personalization
$180k+/yrRemote7+ YOEML Engineering

Design and productionize ML, deep learning, and LLM models for personalization, recommendations, and search systems. Requires 7+ years building production ML/AI with business impact and strong cross-functional collaboration skills.

Talkiatry

Talkiatry

United States

Staff AI Enablement Engineer
$190k+/yrRemote8+ YOEML Engineering

Staff-level engineer responsible for building AI agents and automation, evaluating developer AI tools, and driving adoption across the engineering organization. Requires 8+ years of software engineering experience plus production experience with LLMs, agentic systems, and applied machine learning.

Nuro

Nuro

Mountain View, CA

Senior/Staff Engineer, Machine Learning - Online Mapping
$194k+/yrOn-site7+ YOEML Engineering

Develop and productize online mapping models for autonomous navigation using real-world sensor data. The role requires deep ML expertise, robotics or computer vision experience, strong Python and deep learning framework skills, and a staff-level ability to deliver practical solutions.

Nuro

Nuro

Mountain View, CA

Senior/Staff Software Engineer, ML Inference Platform
$194k+/yrOn-site5+ YOEML Engineering

Build and operate ML infrastructure for autonomy teams, including training and deployment pipelines, model observability, inference serving, and compiler platforms across hardware targets. Requires a degree, 3+ years of relevant experience, Python proficiency, and distributed-systems expertise.