AR

Anirudh Ravula

Generative AI Engineer

Login to See Full Details $150,000/yearly Active

No profile blueprint available for this candidate.

Job Compatibility Score

Generative AI Engineer

85%

Total Score: 85/100

Key Insights:

Anirudh is a strong, production-focused candidate who is an excellent match for this Generative AI Engineer role. His resume demonstrates deep, hands-on experience with the core requirements: building and deploying RAG systems, fine-tuning LLMs, and using frameworks like LangChain. His work at Humana is particularly relevant, showing he can deliver scalable, low-latency AI applications in a complex, regulated domain (Healthcare). The AWS Generative AI certification is a significant plus.

He scores highly on Primary Skills, Tools, and Domain Expertise. The slight deductions come from his current title not being an exact match ("AI/ML Engineer" vs. "Generative AI Engineer") and some secondary skills being more implied than explicitly detailed. His experience level is ideal—neither under nor overqualified.


Candidate Evaluation Table

Category Details from Job Description Claimed Experience Relevant Experience Evidence from Resume Score
Job Titles Generative AI Engineer 5+ years (from summary) 1+ year (direct GenAI work at Humana) "AI/ML Engineer" at Humana (Jan 2024 – Present). Previous role was "Software Engineer." 12/15
Primary Role-Based Skills Build/deploy applications using LLMs (chatbots, copilots) Not explicitly claimed per skill. 1+ year. Architected RAG assistant serving 50K+ daily queries. "Designed RAG assistant for claims audit using LangChain and Pinecone... serves 50K+ daily queries." 18/20
Design prompt strategies and optimize outputs Not explicitly claimed. 1+ year. Implied in RAG and fine-tuning work; explicit in projects. Project: "Enhanced SQL generation accuracy by 35% using RAG... specialized prompt tuning."
Fine-tune and evaluate models Not explicitly claimed. 1+ year. Owned fine-tuning pipeline for Llama 3.2-3B. "Owned fine-tuning pipeline for Llama 3.2-3B with 4-bit QLoRA... collaborated... on evaluation."
Develop pipelines using LangChain, LlamaIndex LangChain claimed in skills. 1+ year. Used LangChain and LangGraph in production and projects. "Designed RAG assistant... using LangChain." Project: "Agentic RAG Analytics System | LangGraph."
Implement RAG systems Not explicitly claimed. 1+ year. Architected production RAG system and project. "Designed RAG assistant for claims audit..." and "Architected multi-agent NL-to-SQL system."
Secondary Skills Integrate AI models with backend systems and APIs Not explicitly claimed. 5+ years. Extensive API and backend integration experience. "Integrated Epic HL7 API integration" at Humana. "Led integration... via Salesforce CRM APIs" at TCS. 9/10
Ensure data privacy, security, compliance Not explicitly claimed. 1+ year. Worked under HIPAA constraints. "Navigated complex healthcare data under HIPAA constraints" in summary.
Monitor performance, reduce hallucinations Not explicitly claimed. 1+ year. Implied in monitoring and evaluation tasks. "Configured Prometheus/Grafana dashboards for real-time alerting." Focus on accuracy metrics in RAG.
Collaborate with product, engineering, data teams Not explicitly claimed. 5+ years. Evidence of cross-functional work. "Collaborated with applied research team." "Partnered with DevOps." "Driving cross-team collaboration."
Tools & Platforms LangChain, LlamaIndex (or similar) LangChain listed in skills. 1+ year. LangChain used in production; LangGraph in projects. Technical Skills list includes LangChain, LangGraph. Evidence in Humana role and projects. 10/10
Certifications Not specified in JD. Holds relevant certifications. N/A "AWS Certified: Generative AI Developer – Professional", "AWS Certified: Machine Learning Engineer – Associate" 5/5
Experience Level Likely Mid to Senior Level (3-7 years estimated from responsibilities) 5+ years total (AI/ML Engineer). 5+ years in software/ML engineering, with 1+ year focused on GenAI. Professional experience from Jun 2019 to Present (5+ years). Deep GenAI work from Jan 2024. 10/10
Domain Expertise Not explicitly specified. Implied need for experience in building real-world applications. Healthcare (1+ year), Retail/E-commerce (3 years at TCS). 1+ year in Healthcare, a complex, regulated domain analogous to many enterprise AI use cases. "Navigated complex healthcare data under HIPAA constraints" at Humana. CLV modeling for retail at TCS. 10/10
Consistency Across Summary, Experience, and Education N/A Summary claims 5+ years leading ML/GenAI systems. Experience and projects fully support the summary's claims of production GenAI, RAG, and MLOps work. Summary highlights are directly evidenced in Humana role and personal projects (RAG, fine-tuning, MLOps). Education (M.S. in OR & Analytics) is relevant. 10/10
> >