SV
Shabari Vignesh
Generative AI Engineer
No profile blueprint available for this candidate.
Job Compatibility Score
Generative AI Engineer
70%Alright, let's break this down. This candidate has a strong data engineering foundation and is actively moving into Generative AI. The JD is for a pure-play Generative AI Engineer, so we're looking for direct, hands-on experience with LLMs, RAG, and model integration, not just adjacent data skills.
Total Score: 70/100
Key Insights:
- Strong Emerging Fit: The candidate is transitioning from Data Engineering into AI Engineering, with the most recent role at Swirepay providing highly relevant, project-based experience in building LLM applications (RAG systems, agents with LangChain, evaluation frameworks). This is recent and impactful.
- Primary Skills Gap: While they have built systems using LLMs, the resume lacks explicit evidence of core GenAI responsibilities like model fine-tuning or deep prompt strategy design. The experience is more in applying and safeguarding pre-built models.
- Tool & Platform Alignment is Excellent: Direct, recent experience with AWS Bedrock and LangChain matches the JD's core requirements perfectly. This is a major strength.
- Experience Level is a Match: ~5 years total experience with ~1 year of focused GenAI project work aligns well with what the role likely expects (not a senior lead, but a capable hands-on engineer).
- Domain Agnostic: Lacks specific domain expertise (e.g., Healthcare, Legal), but the financial data grounding at Swirepay shows an ability to work in a compliance-sensitive environment, which is a plus.
📊 Candidate Evaluation Table
| Category | Details from Job Description | Claimed Experience | Relevant Experience | Evidence from Resume | Score |
|---|---|---|---|---|---|
| Job Titles | Generative AI Engineer | "Experienced AI Engineer with 5+ years" | ~1 year of direct Generative AI project work. 5+ years in broader data/ML engineering. | "AI Engineer" at Swirepay (Jan 2025-Present). Previous titles were Data Engineer/Consultant. | 12/15 |
| Primary Role-Based Skills | Build/deploy apps using LLMs (chatbots, copilots) | Not explicitly claimed in years for this skill. | ~1 year. Built a "ChatGPT-style Agent" and "Generative AI applications" for Q&A and summarization. | Swirepay Project 2: "Delivered an agent-based conversational analytics system using AWS Bedrock and LangChain." | 8/20 |
| Design prompt strategies & optimize outputs | Not explicitly claimed. | Demonstrated through implementation. Used "multi-step prompt workflows with structured outputs." | Swirepay Project 2: "Improved successful query completion rates... by introducing multi-step prompt workflows." | 6/20 | |
| Fine-tune and evaluate models | Not explicitly claimed. | Demonstrated model evaluation, not fine-tuning. "Implemented LLM evaluation frameworks, reducing 28% hallucination." | Swirepay Project 1: "Implemented LLM evaluation frameworks..." | 5/20 | |
| Develop pipelines using LangChain/LlamaIndex | Not explicitly claimed in years. | ~1 year of direct hands-on use. | Swirepay Project 2: "Delivered an agent-based... system using AWS Bedrock and LangChain." | 7/20 | |
| Implement RAG systems | Not explicitly claimed. | ~1 year. Core architecture of the Q&A system was RAG-based (grounding answers in data lake). | Swirepay Project 2: "Designed the system to enforce deterministic SQL... ensuring responses were always grounded in curated data lake tables." | 7/20 | |
| Secondary Skills | Integrate AI models with backend systems/APIs | Not explicitly claimed for AI. | Strong evidence via data engineering. Built integrations for data pipelines and the AI agent used internal APIs. | Swirepay Project 2: "explicit tool invocation," "low-latency AWS Lambda APIs." Historically built many API-based ETL pipelines. | 8/10 |
| Ensure data privacy, security, compliance | Not explicitly claimed. | Demonstrated through design of guardrails and safety controls for financial data. | Swirepay Project 3: "AI & Data Observability, Guardrails, and Adversarial Testing... preventing unsafe query execution." | 7/10 | |
| Monitor performance, reduce hallucinations | Not explicitly claimed. | Directly addressed. Built observability and reduced hallucinations by 28%. | Swirepay Project 1 & 3: "Implementing LLM evaluation frameworks, reducing 28% hallucination..." and "Built an AI observability layer." | 8/10 | |
| Tools & Platforms | LangChain, LlamaIndex (or similar) | Not explicitly claimed in years. | ~1 year with LangChain. No mention of LlamaIndex. | Swirepay Project 2: Explicit mention of using LangChain. | 9/10 |
| Certifications | Not specified in JD. | AWS Generative AI Professional (in progress), other AI/Data certs. | Holds relevant, modern certifications. | Listed under Awards & Certification: "AWS Generative AI Professional certification - Inprogress." and IIT Madras NPTEL AI cert. | 4/5 |
| Experience Level | Likely Mid-Level (3-7 years in AI/ML/Data, with recent GenAI focus). | 5+ years total (AI/Data Engineering). | ~5 years in data/ML engineering, with ~1 year of concentrated, production-level GenAI work. | Timeline shows progression from Data Consultant (2019) to Data Engineer (2024) to AI Engineer (2025). | 9/10 |
| Domain Expertise | Not specified. Implied need for experience in production, real-world use cases. | Financial/Payments (1 yr), Sales/Tech (3 mos), Energy/Utilities (2 yrs), Airlines/Manufacturing (1.5 yrs). | Recent experience in financial data (Swirepay) which demands accuracy and has compliance aspects. | Swirepay: Worked with merchant financial transaction and inventory data. | 7/10 |
| Consistency Across Summary, Experience, and Education | N/A | Summary claims "AI Engineer with 5+ years." | Experience shows a clear, recent pivot into AI Engineering role, supported by projects and skills list. MS in Applied Data Science supports the transition. | Summary, current job title (AI Engineer), and projects (Swirepay AI projects) are fully aligned. Education is relevant. | 9/10 |
Final Note: This candidate is a high-potential contender for the role. They have the most important tool experience and have successfully delivered production GenAI applications. The main interview focus should be on probing the depth of their prompt engineering and model fine-tuning knowledge, as their resume shows more strength in application development and evaluation. They have proven they can build and deploy the systems the role requires.