Senior Prompt Engineering Engineer

Fuku; San Francisco (CA); Hybrid; USD 170,000 - 240,000; Full time

Benefits offered by this job

Equity

Healthcare

Learning stipend

Gear stipend

Unlimited PTO

Job summary

Entbot seeks a Senior Prompt Engineering Engineer to own the full lifecycle of intelligent workflow design, from prompt research to production rollout in collaboration with product and customer teams.

You will design multi-agent prompt strategies, build evaluation harnesses, and partner with customers to translate requirements into reliable AI behaviors while instrumenting everything built for measurable outcomes.

Qualifications

• 4+ years shipping ML/AI or NLP systems.
• 1–2 years focused on LLM prompt/agent engineering.
• Familiar with Claude, GPT, Gemini or open-source families.
• Strong Python or TypeScript fundamentals.
• Experience with LangChain/LangGraph, LlamaIndex, or custom eval harnesses.

Responsibilities

• Design, test, and ship multi-agent prompt strategies across core products.
• Build automatic evaluation harnesses, red-teaming suites, and telemetry dashboards.
• Collaborate with product, solutions, and customers to align AI behavior.
• Productionize prompt/tooling bundles as reusable components and document best practices.
• Track frontier LLM ecosystem and recommend cost-effective adoption paths.

Skills

Prompt engineering

Python

TypeScript

LangChain

LangGraph

LlamaIndex

Evaluation stacks

Team collaboration

Tools

Weigths & Biases

Claude

GPT

Gemini

Job description

About Entbot

Entbot is building an autonomous operations copilot for enterprise teams. The company combines frontier LLMs with purpose-built retrieval, evaluation, and analytics pipelines, enabling GTM, ops, and support organizations to deploy AI workflows safely.

Role

Entbot is seeking a Senior Prompt Engineering Engineer who will own the full lifecycle of intelligent workflow design. This includes prompt research, automated evaluation, guardrail instrumentation, tool integration, and production rollout in collaboration with product and customer teams.

What you'll do

• Design, test, and ship multi-agent and multi-turn prompt strategies across core products such as ops copilot, auto-reply, research agents, and workflow builder.
• Build automatic evaluation harnesses, red-teaming suites, and telemetry dashboards to quantify quality, safety, and latency metrics for every release.
• Partner with product, solutions, and enterprise customers to translate ambiguous requirements into reliable AI behaviors, including tool/knowledge grounding strategies.
• Productionize prompt/tooling bundles as reusable components in the internal SDK; document best practices and mentor other engineers and designers.
• Track the frontier LLM/model ecosystem, benchmark new releases, and recommend adoption paths that balance capability, cost, and compliance.

What we're looking for

• 4+ years of experience shipping ML/AI or applied NLP systems, with at least 1–2 years focused on LLM prompt or agent engineering.
• Deep familiarity with Claude, GPT, Gemini, or open-source families, as well as evaluation stacks such as Ragas, DeepEval, LangSmith, Weights & Biases, etc.
• Strong software fundamentals in Python or TypeScript, plus experience orchestrating workflows via LangChain/LangGraph, LlamaIndex, custom eval harnesses, or similar tools.
• Comfort collaborating directly with customers, product, and go-to-market partners; excellent written documentation habits.
• A bias toward experimentation and measurable outcomes, with a default to instrumenting everything built.

Nice to have

• Experience deploying AI copilots into regulated industries, multilingual surfaces, or high-volume support funnels.
• Background in retrieval (vector databases), structured reasoning, toolformer-style call planning, or synthetic data pipelines.
• Contributions to open-source LLM tooling or published best-practice guides.

Why Entbot

• Early seat on a senior, product-minded team shipping into real Fortune 500 workflows.
• Competitive cash and equity, full healthcare, stipends for learning and gear, unlimited PTO with two yearly company shutdown weeks.
• Hybrid-friendly: HQ in San Francisco with remote flexibility across North America time zones.