Prompt Engineer Jobs in Manhattan, NY (NOW HIRING)

Remote (US-Based) · Optional hybrid in New York, NY

About LockedIn AI

LockedIn AI is the #1 real-time AI interview and meeting copilot, trusted by over one million users worldwide. We are a fast-growing company building the most advanced career preparation platform on the market.

Our platform delivers real-time, AI-powered assistance during live job interviews, coding assessments, and professional meetings — helping candidates communicate with clarity, confidence, and competence.

Role Overview

We are looking for a creative, technically sharp Prompt Engineer to design, craft, and optimize the prompts and instruction sets that power LockedIn AI’s core AI experience. This is a hands-on, high-leverage role — the quality of every AI-generated response our users see flows directly through your work.

You will own the full prompt lifecycle — from understanding user needs and model behavior, to writing and testing prompt architectures, to evaluating output quality and iterating based on real-world performance data. You will work across multiple LLM providers (OpenAI, Anthropic, open-source models) and develop prompt strategies that maximize accuracy, relevance, tone, and speed while minimizing hallucination, cost, and latency.

The ideal Prompt Engineer combines exceptional language skills with a deep, practical understanding of how large language models work. You think in systems — building reusable prompt templates, chain-of-thought architectures, and evaluation rubrics — not just one-off instructions. You are obsessive about output quality and relentless about testing and iteration.

Key Responsibilities

• Design, write, and optimize production-grade prompts and system instructions that drive LockedIn AI’s real-time copilot across interview coaching, coding assistance, and meeting support use cases
• Develop and maintain prompt architectures including system prompts, few-shot examples, chain-of-thought reasoning, role-based instructions, and multi-turn conversation management
• Apply advanced prompt engineering techniques — including zero-shot, few-shot, chain-of-thought, self-consistency, tree-of-thought, and retrieval-augmented prompting — to maximize output quality for different product scenarios
• Build and maintain a structured prompt library and repository, documenting prompt patterns, version history, and performance benchmarks for reuse across the platform

Prompt Testing, Evaluation & Quality Assurance

• Design and execute rigorous prompt evaluation frameworks with clearly defined metrics — including accuracy, relevance, tone alignment, hallucination rate, response completeness, and latency
• Build and maintain benchmark datasets, golden answer sets, and scoring rubrics to systematically measure prompt performance across diverse user scenarios and edge cases
• Conduct systematic A/B tests and comparative experiments across prompt variations, model versions, and LLM providers to identify the highest-performing configurations
• Analyze prompt failure modes, identify patterns in low-quality outputs, and rapidly iterate on prompt designs to close quality gaps
• Work across multiple LLM providers (OpenAI, Anthropic, Google AI, open-source models) to understand model-specific behaviors, strengths, and limitations — and tailor prompt strategies accordingly
• Develop model routing logic and prompt adaptation layers that optimize for the best combination of quality, latency, and cost across different use cases and user segments
• Monitor and adapt prompts as models are updated or replaced, ensuring consistent output quality through model version changes and provider migrations
• Track and optimize token usage, prompt length, and inference costs — balancing response quality with sustainable unit economics

Retrieval-Augmented Generation (RAG) & Context Management

• Design prompts that effectively leverage retrieval-augmented generation (RAG) pipelines, ensuring AI responses are grounded in accurate, relevant, and up-to-date knowledge sources
• Develop context management strategies for real-time, multi-turn conversations — optimizing how conversation history, retrieved documents, and user context are structured within prompt context windows
• Collaborate with engineering to improve how retrieved content is formatted, ranked, and injected into prompts to maximize groundedness and minimize hallucination
• Test and optimize prompts under varying context window constraints, ensuring robust performance as conversation length and complexity increase

Cross-Functional Collaboration & Knowledge Sharing

• Partner with product, engineering, research, and content teams to understand user needs, product requirements, and domain-specific language — translating them into effective prompt designs
• Collaborate with data and analytics teams to build feedback loops that connect real-world user interactions and quality signals back to prompt iteration cycles
• Document prompt engineering best practices, design patterns, and lessons learned — building organizational knowledge that scales beyond any single contributor
• Stay current on the latest developments in prompt engineering, LLM capabilities, and generative AI research — and proactively apply new techniques to improve LockedIn AI’s AI experience

Responsible AI & Output Safety

• Ensure all prompts comply with LockedIn AI’s privacy-first design philosophy and user data handling guidelines
• Design safety guardrails, content filters, and fallback instructions within prompts to prevent harmful, biased, inappropriate, or off-topic AI outputs
• Test prompts against adversarial inputs, jailbreak attempts, and edge cases to identify and close safety vulnerabilities before they reach production
• Champion responsible prompt engineering practices — proactively addressing bias, fairness, and transparency in AI-generated content

Required QualificationsExperience

• 2+ years of professional experience in prompt engineering, NLP, conversational AI, or a closely related role working hands-on with large language models in production
• Demonstrated experience designing and optimizing prompts for LLM-powered products or features — with measurable improvements in output quality, accuracy, or user satisfaction
• Hands-on experience with multiple LLM providers and APIs (OpenAI, Anthropic, Google AI, or open-source models) including deep familiarity with model-specific behaviors and limitations
• Experience building prompt evaluation frameworks, running systematic experiments, and using data to drive prompt iteration decisions
• Startup or high-growth environment experience preferred — comfort working in ambiguity and shipping fast

Education

• Bachelor’s degree in Computer Science, Linguistics, Computational Linguistics, NLP, Data Science, or a related field.
• We value demonstrated prompt engineering skill, a strong portfolio, and practical results over credentials.

Technical Skills

• Deep expertise in prompt engineering techniques including zero-shot, few-shot, chain-of-thought, self-consistency, role-based prompting, and retrieval-augmented prompting
• Strong understanding of how large language models work — including tokenization, context windows, temperature, top-p sampling, model limitations, and failure modes
• Proficiency in Python for prompt testing automation, evaluation scripting, and data analysis
• Experience with prompt management and evaluation tools (LangChain, LlamaIndex, Weights & Biases, Promptlayer, or similar)
• Familiarity with retrieval-augmented generation (RAG) architectures and how prompt design interacts with retrieved content
• Working knowledge of API integration, version control (Git), and basic data analysis (SQL, pandas)

Strategic & Soft Skills

• Language-first mindset: you have an exceptional command of language and understand that word choice, structure, and framing fundamentally change AI output quality
• Analytical rigor: you test systematically, measure precisely, and make prompt decisions based on data rather than intuition
• Creative problem-solving: you can approach the same problem from multiple angles, crafting unconventional prompt strategies when standard approaches fall short
• Strong written and verbal communication — you can document prompt architectures clearly, explain tradeoffs to cross-functional teams, and present evaluation results to non-technical stakeholders
• Self-starter mentality: you thrive with autonomy, move fast, and take ownership of prompt quality end-to-end

Preferred Qualifications

• Experience with real-time AI systems, conversational AI, or latency-critical prompt optimization
• Background in speech-to-text integration, multi-modal prompting, or real-time audio context handling
• Experience with agentic prompt architectures, tool-use prompting, or multi-step reasoning chains
• Familiarity with prompt security — including defense against prompt injection, jailbreaking, and adversarial prompt manipulation
• Background in linguistics, creative writing, journalism, or content strategy — bringing a language-native perspective to prompt design
• Experience in the career tech, edtech, or SaaS B2C space
• Contributions to open-source prompt engineering tools, published prompt research, or a public portfolio of prompt engineering work
• Prior startup founding or early employee experience (Seed to Series A stage)

What We OfferEquity

Meaningful early-stage equity — be a true co-owner of what we're building

Impact

Your work directly powers a product used by 1M+ people worldwide

Team

Join a lean, ambitious team where every individual matters

Flexibility

Remote-first culture with optional co-working in New York City

Growth

Be part of a bootstrapped rocket ship approaching its next growth phase

Culture

User-obsessed, feedback-driven, and built for speed

Why Join LockedIn AI?Category-defining product

We pioneered the dual-layer AI copilot + human assist model for interviews — no one else has it.

Massive market

The AI career tools space is exploding, and we’re the #1 rated platform with 1M+ users.

Own the words that matter most

Every AI response our users see flows through your work — you directly control the intelligence and quality of the product experience.

Work across multiple frontier LLMs daily, experimenting with the latest models, techniques, and prompt architectures.

High-leverage, high-visibility role

Prompt engineering is the single highest-leverage skill at an AI-native company — small changes in your work produce massive changes in product quality.

• Any relevant portfolio work, GitHub repos, or technical writing (optional but encouraged)

LockedIn AI is committed to building a diverse and inclusive team. We welcome applicants of all backgrounds, identities, and experiences. Employment decisions are made based on merit, qualifications, and business needs.

#J-18808-Ljbffr