Generative AI Engineer

Company: LockedIn AI
Employment Type: Full-Time
Work Model: Remote (US-Based) · Optional hybrid in New York, NY
Location: New York, NY (Remote-first)
Reports To: Co-Founder / CEO
Compensation: $160,000 – $230,000 USD / year

About LockedIn AI

LockedIn AI is the #1 real-time AI interview and meeting copilot, trusted by over 1M+ users worldwide. We build advanced AI systems that help candidates perform better in live interviews, coding assessments, and professional communication.

Our platform sits at the frontier of applied generative AI — delivering real-time, context-aware assistance powered by large language models, retrieval systems, and intelligent orchestration layers.

Role Overview

We are looking for an innovative, production-focused Generative AI Engineer to design and build the systems that power real-time AI generation inside our core product.

This is where the “magic layer” lives — every response generated by the copilot flows through systems you design, optimize, and deploy.

You will work on:

Real-time LLM-powered response generation
RAG (Retrieval-Augmented Generation) systems
Prompt architectures and multi-model orchestration
Safety guardrails and output control systems
Low-latency production AI pipelines

Your work directly impacts 1M+ users in live, high-stakes scenarios.

Key Responsibilities
Generative AI System Design
Build end-to-end LLM-powered generation systems
Design prompt pipelines, context injection, and multi-step reasoning flows
Develop agentic workflows (tool use, function calling, structured outputs)
Optimize generation for real-time latency and coherence
RAG & Knowledge Systems
Build production-grade retrieval-augmented generation pipelines
Design embedding, indexing, and vector search systems
Implement hybrid retrieval (dense + sparse + reranking)
Maintain knowledge bases for interview, coding, and domain content
Output Quality & Safety Engineering
Build hallucination detection and factual grounding systems
Implement safety filters (toxicity, PII, jailbreak protection)
Design response scoring and post-processing pipelines
Control generation parameters for consistency and reliability
Model Integration & Orchestration
Integrate multiple LLM providers (OpenAI, Anthropic, open-source models)
Build intelligent model routing systems based on cost, latency, and quality
Optimize inference using streaming, caching, and batching strategies
Fine-tune models using LoRA, RLHF, or DPO when needed
Evaluation & Monitoring
Build automated generation evaluation pipelines (LLM-as-judge, RAG metrics, etc.)
Monitor hallucination rates, latency, and quality degradation
Design A/B testing systems for prompts and model strategies
Continuously improve generation quality through data-driven iteration
Cross-Functional Collaboration
Work with product, engineering, and AI research teams
Translate product needs into generative AI system designs
Defend against prompt injection and adversarial attacks
Ensure privacy-first and safe AI output behavior
Required Qualifications
Experience
3+ years building production LLM or generative AI systems
Experience shipping real-world AI features end-to-end
Strong understanding of RAG, prompt engineering, and LLM pipelines
Experience in fast-paced startup or product environments
Technical Skills
Strong Python skills and LLM frameworks (LangChain, LlamaIndex, Hugging Face, etc.)
Deep understanding of transformers, tokenization, and decoding strategies
Experience with vector databases (Pinecone, Weaviate, Qdrant, etc.)
Familiarity with model fine-tuning (LoRA, RLHF, DPO)
Experience building scalable APIs (FastAPI or similar)
Knowledge of LLM evaluation frameworks (RAGAS, DeepEval, etc.)
Soft Skills
Strong ownership and product thinking
Deep obsession with output quality and user experience
Ability to explain complex AI systems clearly
Fast execution in ambiguous environments
Preferred Qualifications
Experience with real-time streaming AI systems
Agentic AI systems (function calling, tool use, multi-step reasoning)
Experience with prompt injection defense and AI security
Multimodal AI or speech-to-text + LLM pipelines
Model optimization (quantization, distillation, inference acceleration)
SaaS or consumer AI product experience
Open-source contributions in generative AI
What We Offer
Early-stage equity ownership
Direct impact on 1M+ users
Remote-first flexibility
High-growth AI-native environment
Ownership of core generative AI systems
Fast-paced execution culture
Why Join LockedIn AI?
Category-defining AI interview copilot platform
Massive global user base (1M+ users)
You own the generation layer powering real-time AI responses
Work at the frontier of applied generative AI systems
High autonomy, high impact, fast iteration environment
How to Apply

Please submit:

Resume / CV
Short note explaining why you want to join LockedIn AI
Whether you’ve used the product
Optional: GitHub, projects, or generative AI work samples