Open to opportunities

Sushanth Reddy

@sushanthreddy1

Message

LLM Engineer building production GenAI systems that reduce latency and hallucinations.

United States

Message

What I'm looking for

I seek hands-on roles building production GenAI systems with strong MLOps, observability, and cross-team impact, where I can reduce latency and improve safety.

I am an LLM Engineer with 3+ years building production-ready GenAI systems, specializing in retrieval-augmented generation, fine-tuned instruction models, and latency and hallucination reduction. I have shipped RAG services, implemented LoRA fine-tuning, and designed evaluation and drift-monitoring pipelines adopted by multiple teams.

I combine ML engineering, MLOps, and product-minded deployment experience to deliver scalable, observable services—deploying microservices on Kubernetes with autoscaling and tracing, establishing CI/CD and model tracking, and producing measurable impact such as 35% p95 latency reduction and approximately $15K/month savings in agent time.

Experience

Work history, roles, and key accomplishments

Current

Generative AI Engineer

Current

Lorvenk Technologies

Feb 2025 - Present (1 year 4 months)

Built a FastAPI + LangChain + FAISS RAG service that cut retrieval p95 latency by 35% and implemented LoRA fine-tuning to reduce token usage by 20%, maintaining p95 latency under 800 ms with Kubernetes autoscaling and tracing.

Lang Chain Faiss fastAPI Kubernetes Distributed Systems Traces

Data Scientist

Molina Healthcare

Dec 2024 - Feb 2025 (2 months)

Improved document triage F1 by 8–12% using LLM summarization and classification pipelines and developed an evaluation harness with gold sets and human rubrics for safety and drift monitoring.

Classification Grafana Logging F1 Optimization

Machine Learning Engineer

Technology Hub Inc

Mar 2024 - Dec 2024 (9 months)

Delivered an LLM-based Client Automation Assistant that saved ~15 hours/agent/month, developed a retrieval-augmented prompt optimizer reducing manual edits ~30%, and implemented CI/CD with MLflow and GitHub Actions for AWS ECS deployments.

MLFlow GitHub Actions AWS ECS LLM Prompts Optimization Automation

Machine Learning System Engineer

Tata Consultancy Services

Aug 2021 - Aug 2022 (1 year)

Built Azure Data Factory and Databricks pipelines for multi‑TB ingestion and retraining, developed logistic regression and decision tree models improving forecast accuracy by 9%, and created Power BI dashboards for SLA and pipeline health tracking.

Azure Data Factory Databricks Logistic Regression Decision Trees Power BI Pyspark