About me
Innovative and results-driven ML Engineer focused on generative AI and Transformer-powered applications. I currently work on large-scale LLM inference systems at Panasonic Avionics, where I optimize latency, throughput, and infrastructure cost across production environments.
ML Engineer & Applied GenAI Specialist
I have delivered impactful systems across cybersecurity, document AI, and LLM applications. My work spans guardrails, retrieval pipelines, inference acceleration, and end-to-end data transformation workflows. I enjoy turning ambiguous business problems into measurable ML outcomes with clean engineering execution.
- Birth Date: 18 September 2001
- Website: Portfolio
- Phone: +91 7976090859
- City: Pune, Maharashtra, India
- Role: Full-time ML Engineer
- Degree: B.Tech (CSE)
- Email: sharmaabhiram1809@gmail.com
- Open to: High-impact AI collaborations
I care about building reliable AI systems that are both technically sound and business-aligned—from proof-of-concept to production. I bring a blend of deep NLP expertise, infrastructure ownership, and strong product intuition.
Facts
A quick snapshot of my recent work and impact across production LLM systems and applied AI projects.
Projects Delivered
AI/ML Implementations
Years Building with AI
Skills
Core strengths across production LLM deployment, NLP pipelines, and practical ML engineering. I focus on shipping measurable outcomes, not just experiments.
Experience & Education
A concise timeline of my professional work, measurable impact, and academic background.
Summary
Abhiram Sharma
Innovative and results-driven Computer Science engineer advancing generative AI and Transformer technologies at scale. Proven record of accelerating inference systems, improving AI safety, and delivering production-ready NLP solutions.
- Pune, Maharashtra, India
- +91 7976090859
- sharmaabhiram1809@gmail.com
- github.com/abhiram1809
Education
B.Tech in Computer Science Engineering
2019 - 2023
Amity University Rajasthan, Jaipur
B1 - German Language
February 2025
Goethe Institute Delhi
Professional Experience
Full-time ML Engineer
July 2025 - Present
Panasonic Avionics, Pune
- Augmented LLM inferencing with KubeRay: Orchestrated Kubernetes on EKS to autoscale workloads using Prometheus metrics, cutting cold-start latency by 900%, improving throughput from 83 tok/s to 347 tok/s, and reducing EC2 compute costs by 5–6x.
Data Scientist / AI-ML Engineer (Consultant for Panasonic Avionics)
February 2025 - July 2025
Calsoft Inc, Pune
- Guardrail Development: Built input/output assessment guardrails using open and closed source technologies, achieving an 88% safer AI system.
- LLM Inferencing: Engineered a WAF-fortified accelerated inference pipeline with vLLM, reaching 80 tok/s for proprietary coding and application workflows.
Data Scientist
September 2023 - January 2025
Softsensor.ai, Jaipur
- Cyber Security Chatbot: Developed core logic for Text2SQL and unstructured MITRE document query workflows for precise log and attack insights.
- Document Translation: Created end-to-end translation software preserving tables and diagrams while translating diverse document formats.
- Claims Automation: Led full-cycle unstructured-to-structured transformation for letters, emails, and SRRs with interlinked document relationships, reducing extraction cost by up to 85%.
- R&D: Contributed to research in topic modeling, ColBERT reranking, LLM finetuning, and multimodal data ingestion pipelines.
Services
I help teams design, ship, and scale practical GenAI systems. Here are the core service areas where I can contribute immediately.
Production LLM Systems
Architecture and deployment of high-throughput inference systems using vLLM, Ray, KubeRay, and Kubernetes, with strong focus on performance, reliability, and cost.
RAG & Knowledge Pipelines
Design and implementation of robust retrieval pipelines, ingestion workflows, and hybrid knowledge systems for enterprise Q&A and assistant use cases.
AI Guardrails & Evaluation
Development of input/output safety layers, policy checks, and automated evaluation loops to make LLM features safer, auditable, and production-ready.
Document AI Automation
End-to-end automation for OCR, translation, extraction, and structuring of complex unstructured documents while preserving layout and context.
Applied NLP & Multimodal ML
Rapid prototyping and delivery across NLP, computer vision, and multimodal AI use cases—from baseline models to optimized, business-facing solutions.
Testimonials
As a professional in my field, I take pride in delivering high-quality services to my clients. Their satisfaction is my top priority, and I am committed to ensuring that they receive the best possible experience working with me. To that end, I am pleased to include a section in my portfolio featuring testimonials from some of my satisfied clients. These reviews offer valuable insights into the quality of my work and the level of service that I provide. I am grateful for their kind words and the opportunity to work with such amazing clients.
What's unique about Abhiram is that he is both an incredibly gifted and competent coder, and is still able to work and communicate with product managers who do not necessarily understand the technical ins and outs of the product he helps create. He has creative solutions in getting around problems; he is very well-read on the literature surrounding machine learning, leading to a great awareness of different models. On top of his abilities, what stands out is his work ethic. Abhiram responds to requests promptly and is always willing to help you with running and improving the programme. He is helping us build a product we are proud of, and we are sure he will continue to build great things and come up with great ideas with whomever he works with in the future.
Yoav
I worked with Abhiram for 8 months. During this time he gave us frequent updates about our project, fantastic explanations and dedicated much of his time to help us develop our ideas and turn our ideas into practical ideas. He acted with the up most professionalism and conducted himself through his knowledge and understanding of computer science, specifically python. He was accessible when we needed to ask questions and very happy to hop onto a call. Overall, I enjoyed working with Abhiram and the knowledge and creative solutions he brought to the table were outstanding.
Oliver
Enim nisi quem export duis labore cillum quae magna enim sint quorum nulla quem veniam duis minim tempor labore quem eram duis noster aute amet eram fore quis sint minim.
Jena Karlis
Store Owner
Contact
I am open to meaningful opportunities in ML engineering and GenAI product development. If you are building with LLMs and need faster, safer, and more reliable systems, let's connect.
Location:
Pune, Maharashtra, India
Email:
sharmaabhiram1809@gmail.com
Call:
+91 79760 90859