.png){kind=logo}
Abhiroopsudansh Karengula
Mid-level AI/ML Engineer specializing in production ML, RAG systems, and MLOps
Connect with Abhiroopsudansh
Abhiroopsudansh already has a relationship with Reval, so a warm intro from us gets a much better response than cold outreach.
Recommended
Already have an account?
About
Built and shipped a widely adopted, production-grade RAG internal search assistant that unified scattered engineering knowledge, deployed as a FastAPI service on Kubernetes with FAISS + LangChain. Demonstrates deep practical expertise in retrieval tuning (chunking, hybrid search, re-ranking) and in making LLM workflows reliable in production via guardrails, monitoring, and evaluation, plus strong cross-functional delivery with non-technical operations teams.
Find your next great hire
Our AI agents source, screen, and vet candidates for your open roles. Get qualified candidates within 48 hours.
Key Strengths
- Built and deployed a production RAG internal search platform (FAISS + LangChain) as a FastAPI service on Kubernetes handling high request volumes
- Improved retrieval accuracy via iterative chunking experiments, document-aware chunking, hybrid search, and re-ranking
- Reduced latency using caching and async processing
- Production reliability focus: evaluation checkpoints, monitoring, guardrails, retries, fallback logic, and human escalation
- Strong model/retrieval/prompt selection process driven by constraints (accuracy, latency, cost, data sensitivity) and real-use-case benchmarking
- Effective collaboration with non-technical stakeholders through workflow discovery, iterative demos, and feedback-driven iteration leading to adoption
- Owned and shipped end-to-end production RAG search platform (frontend/backend/data/infra)
- Production-grade LLM/RAG testing strategy (unit, API-level, offline eval sets with real queries)
- Built guardrails and monitoring for LLM systems (source grounding, fallbacks, sensitive-query handling, quality dashboards)
- Scaled deployment on AWS Kubernetes with autoscaling and reliability focus
- Delivered measurable impact: 400+ engineers adopted; 42% reduction in lookup time/support escalations
- Legacy modernization from batch ML to real-time streaming with Kafka/Spark and shadow deployment validation
- Risk-managed rollout with side-by-side metrics, drift detection, gradual traffic shifting, and rollback via MLflow
- Effective context switching across multiple initiatives with 1–2 week milestone delivery
Like what you see? We'll introduce you to Abhiroopsudansh directly.
Experience
Education
Skills
Languages
Similar Candidates
Senior Machine Learning Engineer specializing in recommender systems, search, and NLP/GenAI
Mid-level AI/ML Engineer specializing in LLM training, RAG, and scalable inference
Senior AI Engineer specializing in LLMs, generative AI, and ML systems
Staff Machine Learning Engineer specializing in search, ranking, and LLM systems
Senior AI Engineer specializing in NLP and large language models
Interested in Abhiroopsudansh?
We'll personally introduce you - no strings attached.
Build your dream team with Reval
Our AI agents source, screen, and vet candidates for your open roles. Get qualified, high-intent candidates on your desk within 48 hours.
Discover more candidates like Abhiroopsudansh
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent