Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

AI Systems Engineer focused on agentic AI, multi-agent systems, and production-grade LLM platforms. Builds retrieval-augmented and policy-aware AI decision systems with strong emphasis on deterministic runtimes, evaluation pipelines, and reliable APIs. Previously engineered LLM/RAG components with performance optimizations, and earlier developed scalable deep spiking neural network training/inference methods. Experienced across cloud infrastructure, orchestration, testing/CI/CD, and research-to-product delivery.…AI Systems Engineer focused on agentic AI, multi-agent systems, and production-grade LLM platforms. Builds retrieval-augmented and policy-aware AI decision systems with strong emphasis on deterministic runtimes, evaluation pipelines, and reliable APIs. Previously engineered LLM/RAG components with performance optimizations, and earlier developed scalable deep spiking neural network training/inference methods. Experienced across cloud infrastructure, orchestration, testing/CI/CD, and research-to-product delivery.

Ana Stanojevic

AI Engineer, Data Scientist, Software Engineer, +2





AI Systems Engineer focused on agentic AI, multi-agent systems, and production-grade LLM platforms. Builds retrieval-augmented and policy-aware AI decision systems with strong emphasis on deterministic runtimes, evaluation pipelines, and reliable APIs. Previously engineered LLM/RAG components with performance optimizations, and earlier developed scalable deep spiking neural network training/inference methods. Experienced across cloud infrastructure, orchestration, testing/CI/CD, and research-to-product delivery.…AI Systems Engineer focused on agentic AI, multi-agent systems, and production-grade LLM platforms. Builds retrieval-augmented and policy-aware AI decision systems with strong emphasis on deterministic runtimes, evaluation pipelines, and reliable APIs. Previously engineered LLM/RAG components with performance optimizations, and earlier developed scalable deep spiking neural network training/inference methods. Experienced across cloud infrastructure, orchestration, testing/CI/CD, and research-to-product delivery.

Available to hire

AI Systems Engineer focused on agentic AI, multi-agent systems, and production-grade LLM platforms. Builds retrieval-augmented and policy-aware AI decision systems with strong emphasis on deterministic runtimes, evaluation pipelines, and reliable APIs.

Previously engineered LLM/RAG components with performance optimizations, and earlier developed scalable deep spiking neural network training/inference methods. Experienced across cloud infrastructure, orchestration, testing/CI/CD, and research-to-product delivery.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Beginner

Language

English

Fluent

German

Intermediate

Serbian

Fluent

Work Experience

Independent AI Systems & Product Development at Independent

March 1, 2025 - Present

Built a career platform for agentic AI and LLM systems covering retrieval, AI decision-making, and multi-agent orchestration. Designed a multi-agent architecture spanning job-signal extraction, profile matching, policy evaluation, and human review workflows. Implemented a production LLM runtime using the OpenAI SDK with Pydantic validation, typed outputs, retrieval, tracing, and deterministic fallbacks. Developed backend AI services, evaluation pipelines, and REST APIs using Python, FastAPI, testing, and CI/CD.

AI/LLM Systems Engineer at Huawei

January 1, 2024 - March 1, 2025

Developed retrieval, inference, and RAG components for LLM systems, including LoRA adaptation and KV-cache optimization. Implemented LLM agents integrating external knowledge via vector search.

Machine Learning Engineer at IBM

October 1, 2019 - December 1, 2023

Developed scalable training and inference algorithms for deep spiking neural networks, combining theoretical advances with practical implementations. Designed optimization techniques enabling exact ReLU-to-SNN conversion and energy-efficient neural inference. Published research in Nature Communications and co-invented patents in neural inference optimization.

Software Engineer Intern (Google Assistant) at Google

August 1, 2018 - February 1, 2019

Worked on BERT-based large-scale NLP systems using C# and Python. Contributed to conversational NLP workflows and answer relevance optimization for large-scale assistant systems.