DEFAULT_SAMPLE_RESUME = """ALEX CHEN Senior AI & Machine Learning Engineer | San Francisco, CA | alex.chen@email.com | (555) 019-2834 | linkedin.com/in/alexchen-ai SUMMARY Passionate Senior AI Engineer with 6+ years of experience designing and deploying scalable deep learning models, RAG architectures, and computer vision systems. Expertise in PyTorch, Python, TensorFlow, Docker, Kubernetes, and LLM fine-tuning. TECHNICAL SKILLS • Languages: Python, C++, SQL, Bash • AI & ML Frameworks: PyTorch, TensorFlow, Scikit-learn, OpenCV, Hugging Face • LLM & RAG: LangChain, LlamaIndex, Vector DBs (Milvus, Qdrant, FAISS), RAG Optimization • MLOps & Cloud: AWS (S3, EC2, SageMaker), Docker, Kubernetes, CI/CD, MLflow PROFESSIONAL EXPERIENCE Senior AI Engineer | TechCorp AI (2022 - Present) • Led development of enterprise RAG search system improving document retrieval latency by 45%. • Fine-tuned 70B parameter LLMs on proprietary datasets using LoRA and QLoRA techniques. • Architected automated MLOps pipelines on Kubernetes serving 2M+ daily active requests. Machine Learning Engineer | DataVision Labs (2019 - 2022) • Trained custom ResNet and YOLO object detection models for real-time video surveillance. • Reduced model inference latency from 120ms to 28ms using TensorRT quantization. EDUCATION B.S. in Computer Science | University of California, Berkeley (2015 - 2019) """ DEFAULT_JOB_DESCRIPTION = """We are seeking a Senior AI/ML Engineer to build next-generation RAG systems, fine-tune open-source Large Language Models (LLMs), and deploy scalable MLOps infrastructure. KEY REQUIREMENTS: • 5+ years of software engineering & ML experience in Python and PyTorch. • Strong expertise in RAG (Retrieval-Augmented Generation), Vector Databases, and LangChain/LangGraph. • Demonstrated experience deploying containerized models on Docker/Kubernetes or Cloud (AWS/GCP). • Experience with MLOps tracking tools (MLflow, Weights & Biases) and CI/CD pipelines. • B.S. or M.S. in Computer Science or related field. """ def generate_ats_score_html(score_pct: int) -> str: """ Renders a glowing neon HTML radial gauge for overall ATS match score percentage. """ color = "#48bb78" if score_pct >= 80 else ("#ed8936" if score_pct >= 60 else "#f56565") return f"""
Overall ATS Compatibility Score
{score_pct}%
""" def generate_subscores_html(keyword_pct: int, skills_pct: int, experience_pct: int, format_pct: int) -> str: """ Renders 4 mini KPI score cards for detailed breakdown. """ return f"""
Keywords
{keyword_pct}%
Skills Match
{skills_pct}%
Experience Fit
{experience_pct}%
Formatting
{format_pct}%
""" def format_skill_badges(matched_skills: list, missing_skills: list) -> str: """ Renders HTML skill badges (Green for matched, Red for missing). """ html = ["
"] html.append("

✅ Matched Qualifications & Skills

") if matched_skills: for s in matched_skills: html.append(f"✓ {s}") else: html.append("No explicit matching skills found.") html.append("

") html.append("

⚠️ Missing Key Competencies from Job Description

") if missing_skills: for s in missing_skills: html.append(f"✗ {s}") else: html.append("No major missing skills identified!") html.append("
") return "".join(html)