Mid-level Backend & ML Engineer specializing in LLM systems and scalable AI pipelines
Bay Area, CASoftware Engineer – ML Pipelines & Model Productionization3 years experienceMid-LevelTechnologyArtificial IntelligenceMachine Learning
ScreenedIdentity Verified
Connect with Sahil
Sahil 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 real-time AI phone agent for small businesses that handles bookings/FAQs/messages using streaming ASR, an LLM with tool-calling, and TTS; deployed to production for multiple paying customers. Demonstrates strong applied LLM reliability practices (tool-first grounding, retrieval, hard-negative testing, and production monitoring) and experience orchestrating multi-step AI workflows with Airflow, Prefect, and AWS Step Functions.
Experience
Software Engineer – ML Pipelines & Model ProductionizationMeta
Language Engineer – AI/LLM SystemsApple
Deep Learning Engineer – Conversational AI (RAG)Stealth Startup
ML Engineer – Conversational AI InfrastructureGoodCall
Applied Scientist – AI & Data EngineeringLiaro.ai
Education
Santa Clara Universitymaster, Computer Science
Tokyo Institute of Technologybachelor, Computer Science
Key Strengths
Built and deployed a production AI phone agent (ASR→LLM→tools→TTS) for paying customers
Latency and real-time voice UX optimization (barge-in, VAD interruption handling, partial transcripts)
Hallucination mitigation via tool-first grounding, retrieval, intent validation, and safe fallbacks
Reliability engineering: structured logging, analytics, prompt evals, offline/edge-case testing, and feedback loops from production
Pragmatic model/retrieval selection based on constraints and evaluation results (smallest model that passes evals)
Effective collaboration with non-technical small-business stakeholders by translating model behavior into business outcomes
Discover more candidates like Sahil
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.