Antriksh Jain
Software Engineer @ Microsoft
About
Software Engineer at Microsoft working on the Azure AI Agents Service — the platform that powers enterprise-grade AI agents in production. My current work involves the control plane infrastructure for Foundry Agents: agent creation, management, and the reliability systems that keep the service running at 99.9% SLA. The team works across agent orchestration, retrieval and file services, and container-based agent execution — essentially the plumbing that makes AI agents work reliably at scale for enterprise customers. Before this, I spent six months on the Azure AI Foundry benchmarking team — owning evaluation coverage for 30+ frontier models (GPT-5, O3, DeepSeek, Mistral, Grok) across quality, cost, performance, and safety. I also built an automated pipeline that eliminated manual benchmarking runs by auto-detecting new models, generating configs, triggering evaluations, and publishing results on a 12-hour schedule. Background in Python, LLM infrastructure, evaluation pipelines, and Azure.
India
Bengaluru
Information Technology & Services
Prompt Engineering, LLM Evaluation, AI Agents, Python (Programming Language), Deep Learning, Fine Tuning, Reinforcement Learning, Large Language Models (LLM), Microsoft Azure, Microsoft Azure Machine Learning, C++
Experience
Software Engineer
Microsoft
Bengaluru, Karnataka, India
• Contributing to Azure AI Agents Service — working on the control plane infrastructure that enables developers to deploy and operate containerised AI agents on Microsoft Foundry at enterprise scale • Working on hosted agents platform: agent creation, lifecycle management (start/stop/update/delete), autoscaling, and maintaining 99.9% SLA for agent deployments across global regions • Previously owned end-to-end benchmarking for 30+ frontier models on Azure AI Foundry (GPT-5, O3, DeepSeek, Mistral, Grok) across quality, cost, performance, and safety • Built an automated evaluation pipeline that auto-detected new models, generated benchmark configs, triggered runs, and published results — reducing manual effort by ~50% • Led safety evaluation of all P0 Azure Direct models across 11 scenario boards for Microsoft Ignite
Software Engineer Intern
Microsoft
Bengaluru, Karnataka, India
• Worked on preference alignment experiments using Direct Preference Optimization (DPO) on the AI platform team — ran training runs across multiple models and datasets and observed measurable improvements in alignment metrics • Integrated DPO training pipeline into Azure ML Studio for reproducible experimentation and model comparison • Gained hands-on exposure to fine-tuning pretrained LLMs and RLHF-based alignment techniques
Education
Netaji Subhas Institute of Technology
Information Technology
Antriksh Jain's Contact Information
Phone
Find the Right Leads
Find Verified Contact Data
What LeadContact does well
Find verified emails, phone numbers, and decision-makers with 98% accuracy.
Find Leads
Find the right people by company, role, industry, location, and more.
925M+ professional profiles
Find Emails
Access verified email addresses for your target contacts.
657M+ emails
Find Phone Numbers
Get cross-validated phone data from multiple top sources.
239M+ phone numbers
More Accurate. Lower Cost.
Find contact data in 1 tool with 98% accuracy
LeadContact integrates leading enrichment tools to deliver more accurate contact data—without paying for each one.
Great conversations start with the right contact.
It’s time to find yours.