Staff AI Engineer

Machinify

. Build LLM-powered products that ship to production .

Posted 11/1/2026full-timeRemote • United StatesLead💰 $210,000 - $280,000 per yearWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in building and deploying LLM-powered products, with strong capabilities in prompt engineering, evaluation, and integration of foundation models. Proficient in Python and TypeScript, with a focus on cost and latency management in production environments.

Highest-signal resume keywords

LLM Application DevelopmentPrompt EngineeringPython ProgrammingTypeScript ProgrammingEvaluation Suite Maintenance

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

LLM-Based FeaturesPrompting TechniquesFunction CallingStructured OutputsContext ManagementEmbedding ModelsVector SearchFine-Tuning ModelsCost AnalysisLatency Awareness

Soft Skills

Clear CommunicationChallenging AI Misuse

Tools & Technologies

ClaudeGPTGeminiLlamaQwenMistralLangGraphInngestTemporalPgvector

Industry Keywords

RAG PipelinesMulti-Step WorkflowsAI-Specific UX PatternsHuman-In-The-Loop WorkflowsLLM SecurityOpen-Source AI Tooling

Tech Stack

Tools & technologies

PythonTypeScript

About the role

Key responsibilities & impact

Build LLM-powered products that ship to production
Design and build LLM applications including RAG pipelines, agents, tool-use systems, structured generation, and multi-step workflows
Own prompt engineering and evaluation, writing evaluations before prompts and treating both as code
Integrate foundation models including Claude, GPT, Gemini, Llama, Qwen, and Mistral
Build production infrastructure including caching, streaming, retries, fallbacks, cost controls, observability, and guardrails
Fine-tune or distill models when prompting is insufficient, using LoRA/QLoRA, SFT, or DPO
Partner with product and design on AI-specific UX patterns such as latency masking, streaming UIs, confidence display, and human-in-the-loop workflows

Requirements

What you’ll need

3+ years of software engineering experience, including at least 1 year shipping LLM-based features in production
Strong Python and TypeScript skills
Deep practical knowledge of prompting techniques, function calling, structured outputs, context management, embedding models, and vector search
Experience building and maintaining an evaluation suite
Comfort with at least one orchestration approach: custom, LangGraph, Inngest, or Temporal
Comfort with at least one vector store: pgvector, Pinecone, Turbopuffer, or Weaviate
Cost- and latency-awareness, including ability to analyze token bills and traces
Clear communication skills and ability to challenge inappropriate use of AI
Experience with agent frameworks and MCP, fine-tuning open-weight models or inference servers, LLM security/evals/red-teaming, and open-source AI tooling are nice to have

Benefits

Comp & perks

Work from anywhere in the US; Machinify is digital-first
Top Medical/Dental/Vision offerings
FSA/HSA
Tuition reimbursement
401(k) with company match
Unlimited PTO
Additional health and wellness benefits and perks
Flexible and trusting environment where you’ll feel empowered to do your best work
Meaningful equity