Senior AI/LLM Inference Engineer

Persistent Systems Limited; Bengaluru; Hybrid; INR 1,200,000 - 2,400,000; Full time

Benefits offered by this job

Flexible hours

Hybrid work

Higher education support

Long service awards

Insurance coverage: life & health for

Employee engagement

Job summary

Persistent Systems Limited is seeking a Senior AI/LLM Inference Engineer to design, optimize, and deploy high-performance LLM inference across CPU, GPU, and edge platforms. You will build evaluation frameworks, benchmark models, and drive experiments in prompt engineering and fine-tuning while ensuring reliability and scalability of AI workloads.

Ideal candidates have 5-10 years in AI systems, strong Python/C++ skills, and hands-on with PyTorch and Transformers.

Qualifications

• 5-10 years of experience in AI systems engineering or related fields.
• Strong programming in Python and modern C++ with debugging, profiling, memory management.
• Deep understanding of Transformer architectures and tokenization.
• Hands-on with PyTorch and Hugging Face Transformers.
• Experience with LLMs (Llama, GPT-family) and evaluation methods.
• Experience building scalable CI/CD for AI platforms.

Responsibilities

• Design high-performance inference pipelines for LLMs across CPU, GPU, and edge.
• Develop evaluation frameworks for reasoning, factuality, and multimodal capabilities.
• Benchmark foundation models with reproducible datasets and metrics.
• Experiment with prompt engineering, RAG, and fine-tuning strategies.
• Create automated evaluation and bias assessment workflows.
• Optimize latency, throughput, and memory in diverse deployments.
• Develop custom operators and kernels for AI workloads.
• Implement vectorized CPU implementations using NEON, AVX2/AVX-512, SSE.

Skills

Python

C++

PyTorch

Transformers

GPU acceleration

CUDA

Quantization

Inference optimization

Profiling

Linux

Education

MS/PhD preferred

Tools

ONNX

Git

CMake

Ninja

Linux

Docker

Job description

We are an AI-led, platform-driven Digital Engineering and Enterprise Modernization partner, combining deep technical expertise and industry experience to help our clients anticipate what's next. Our offerings and proven solutions create a unique competitive advantage for our clients by giving them the power to see beyond and rise above. We work with many industry-leading organizations across the world, including 20 Fortune 50 companies and 4 of the 5 top banks in both the US and India, and numerous innovators across the healthcare ecosystem.

We are seeking a highly skilled Senior AI/LLM Inference & GPU Optimization Engineer to design, optimize, evaluate, and deploy high-performance Large Language Model (LLM) and multimodal AI inference solutions across CPU, GPU, and edge environments. The ideal candidate will combine strong expertise in LLM architectures with systems programming, SIMD optimization, GPU acceleration, quantization techniques, and inference performance engineering. You will play a key role in building scalable AI systems that deliver low-latency, high-throughput inference while maintaining model accuracy and reliability.

• Role: Senior AI/LLM Inference Engineer
• Experience: 5 to 10 Years
• Job Type: Full-Time Employment

What You'll Do:

• Design and optimize high-performance inference pipelines for Large Language Models and multimodal foundation models across CPU, GPU, and edge platforms.
• Build and maintain evaluation frameworks for assessing reasoning, factuality, instruction following, long-context performance, robustness, tool usage, and multimodal capabilities.
• Compare and benchmark foundation models using reproducible datasets, quantitative metrics, qualitative analysis, and failure-mode categorization.
• Design experiments for prompt engineering, Retrieval-Augmented Generation (RAG), fine-tuning strategies, inference-time scaling, and model behavior analysis.
• Develop automated evaluation pipelines, including LLM-as-a-Judge methodologies, human validation workflows, and bias assessment mechanisms.
• Optimize model latency, throughput, memory utilization, and operational efficiency across various deployment environments.
• Implement model quantization strategies, mixed-precision inference, weight compression, and memory optimization techniques.
• Develop and optimize custom operators, inference kernels, and runtime components for AI workloads.
• Create vectorized CPU implementations leveraging ARM NEON, AVX2, AVX-512, and SSE instruction sets.
• Collaborate with AI researchers, platform engineers, and product teams to productionize cutting-edge LLM capabilities.
• Analyze inference bottlenecks using advanced profiling and performance engineering methodologies.
• Deploy and manage production-grade AI inference systems with reliability, scalability, and observability best practices.
• Stay current with advancements in AI acceleration, LLM architectures, inference frameworks, and hardware optimization technologies.

Expertise You'll Bring:

• 5-10 years of experience in AI Systems Engineering, Machine Learning Infrastructure, High-Performance Computing, Systems Programming, or AI Platform Engineering.
• Strong programming expertise in Python and modern C++ with experience in debugging, profiling, memory management, and multithreaded development.
• Deep understanding of Transformer architectures, attention mechanisms, tokenization, embeddings, positional encoding, KV cache optimization, and text generation techniques.
• Hands-on experience with PyTorch, Hugging Face Transformers, and modern LLM development ecosystems.
• Practical experience working with LLMs such as Llama, Qwen, Mistral, Gemma, GPT-family models, or equivalent foundation models.
• Strong expertise in LLM evaluation methodologies, benchmarking frameworks, and model performance measurement.
• Experience implementing Retrieval-Augmented Generation (RAG), prompt engineering, and model fine-tuning solutions.
• Strong understanding of quantization techniques, mixed precision inference, calibration methodologies, weight packing, and numerical accuracy validation.
• Hands-on experience developing and optimizing SIMD-based kernels using ARM NEON, x86 AVX2, AVX-512, or SSE instruction sets.
• Experience with GPU acceleration technologies including CUDA, Metal, OpenCL, DirectML, or equivalent GPU compute frameworks.
• Strong understanding of GPU architectures, memory hierarchies, parallel computing concepts, and AI acceleration techniques.
• Experience with model deployment, inference runtimes, ONNX, model export workflows, and AI serving platforms.
• Proficiency with Linux development environments, Git, CMake, Ninja, compilers, linkers, shared libraries, and ABI compatibility.
• Experience building scalable CI/CD pipelines and production-grade AI platforms.
• Strong analytical, problem-solving, and performance optimization skills.
• Competitive salary and benefits package
• Culture focused on talent development with quarterly growth opportunities and company-sponsored higher education and certifications
• Opportunity to work with cutting-edge technologies
• Employee engagement initiatives such as project parties, flexible work hours, and Long Service awards
• Insurance coverage: group term life, personal accident, and Mediclaim hospitalization for self, spouse, two children, and parents

Values-Driven, People-Centric & Inclusive Work Environment:

Persistent is dedicated to fostering diversity and inclusion in the workplace. We invite applications from all qualified individuals, including those with disabilities, and regardless of gender or gender preference. We welcome diverse candidates from all backgrounds.

• We support hybrid work and flexible hours to fit diverse lifestyles.
• Our office is accessibility-friendly, with ergonomic setups and assistive technologies to support employees with physical disabilities.
• If you are a person with disabilities and have specific requirements, please inform us during the application process or at any time during your employment

Persistent is an Equal Opportunity Employer and prohibits discrimination and harassment of any kind.