.png){kind=logo}
Rohan Keshav Harish
Entry-Level Software Engineer specializing in AWS data pipelines and AI automation
Connect with Rohan
Rohan 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
AI research engineer who has built and tested LLM agents end-to-end, including a Telegram real-time voice-to-typing assistant integrated with calendar scheduling. Emphasizes production concerns (security via mic-triggered activation, multi-model fallbacks, monitoring) and agent predictability using a GPT-3.5-based critic plus structured outputs (Pydantic) and ReAct-style orchestration.
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
- Shipped a production-ready Telegram voice-to-text agent with calendar scheduling
- Designed reliability/security behavior (mic-triggered activation; not always listening)
- Achieved ~90–95% accuracy in user testing for voice-to-text workflow
- Implemented multi-model fallback/backups to handle pipeline failures
- Architected multi-step agent workflows with LangChain tools, ReAct loop, and Pydantic-validated structured outputs
- Improved predictability using an LLM critic to catch invalid tool args, logical plan issues, and repeated failed actions
- Mitigated critic tradeoffs (latency via lightweight prompts; selective checks; confidence thresholds to reduce overcorrection)
- Used real-time monitoring to diagnose and fix agent looping/repeated actions by adding guard conditions
Like what you see? We'll introduce you to Rohan directly.
Experience
Education
Awards
Languages
Certifications
Publications
1 publication
Memberships
Browse Similar
Similar Candidates
Senior Full-Stack Software Engineer specializing in cloud-native distributed systems and AI
Senior AI/ML Engineer specializing in applied AI and scalable backend systems
Staff-level Software Engineer specializing in LLM inference infrastructure and scalable model serving
Senior Full-Stack Engineer specializing in AI/ML platforms and cloud-native systems
Senior AI/ML Engineer specializing in NLP, LLMs, and retrieval systems
Staff Software Engineer specializing in distributed systems and AI infrastructure
Interested in Rohan?
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 Rohan
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent