Sfoglia categorie
Esplora
Fiverr Pro
Italiano
$
USD
Venkata P
@venkata_govind
AIML Professional
India
Inglese
Chi sono
I am an AI/ML professional with 2 years of experience in Data Annotations and Prompt Engineering. Also I have hands-on experience in LLM security evaluation, prompt injection testing, and adversarial AI research. I have a proven track record in identifying jailbreak vectors and designing safety guardrails across architectures like GPT-4 and Claude. I specialize in applying the OWASP Top 10 for LLM Applications to ensure responsible AI deployment.
Competenze
Venkata P
offline •
Tempo di risposta medio: 2 ore
Consulta i miei servizi
Annotazione ed etichettatura dei dati
I will do data annotation, expert prompt engineering, and llm red teaming
Esperienza lavorativa
ML data Associate 2
Amazon
Dec 2024 - Mar 2026 • 1 yr 3 mos
Data Annotation - Text , Image , Video, Red Teaming and Prompt Engineering. GPT 4, Gemini, Claude.
AI Security & LLM Evaluation Engineer
Genpact • Full time
Feb 2024 - Nov 2024 • 9 mos
Improved model accuracy by 25% using Chain-of-Thought and Few-Shot prompting. Conducted adversarial testing, discovering 150+ unique jailbreak vectors to reduce safety violations. Curated synthetic datasets for SFT and RLHF. Evaluated performance across GPT-4, Llama, and Claude architectures to identify bias and security vulnerabilities while maintaining structured evaluation frameworks.
