Technical Architect — AI Systems, Inference & Platform Internals at Accellor

Location: Mountain View, California
Type: Full-time
Level: Entry-level
Posted: Jun 22, 2026

Description

Accellor is hiring a senior Technical Architect for AI Systems, Inference & Platform Internals to design, scale, and optimize the internal AI platform powering ChatGPT/OpenAI-style products, with responsibilities spanning inference runtime, model serving, GPU infrastructure, distributed systems, context engineering, cost optimization, release safety, observability, and production reliability. The role requires 10–12 years of experience plus strong hands-on software and systems engineering skills across Python, a systems/backend language, distributed infrastructure, ML frameworks, GPU programming, and AI/ML platform operations.

Required Skills

Python
Systems programming
Distributed systems
AI/ML systems
GPU programming
ML frameworks

Additional Information

Required Previous Experiences: 10–12 years of experience in software engineering, systems architecture, ML infrastructure, distributed systems, platform engineering, inference systems, cloud infrastructure, or large-scale backend engineering
Preferred Qualifications: Experience with LLM inference, multimodal inference, agent infrastructure, AI assistants, coding agents, or frontier-model serving platforms
Experience with tensor parallelism, pipeline parallelism, model sharding, KV-cache optimization, batching, speculative decoding, streaming inference, and long-context serving
Experience designing context engineering platforms, prompt/version management systems, model-routing frameworks, semantic caching layers, token-budgeting systems, or LLM cost dashboards
Experience profiling GPU workloads with Nsight Systems, Nsight Compute, rocprof, perf, Prometheus, Grafana, OpenTelemetry, or similar tools
Experience with large-scale distributed training, RL infrastructure, checkpointing, ML compiler optimizations, model graph transformations, or training runtime systems
Experience designing release gates, regression detection systems, canary systems, CI/CD validation frameworks, and production safety controls
Experience with evals, model quality measurement, hallucination detection, grounding evaluation, safety testing, and model behavior monitoring

About Accellor

Accellor

Enterprise AI

Accellor transforms enterprises with AI-driven technologies, enabling smarter business strategies, operational efficiency, and personalized customer experiences.

Open roles: 126
New in 30 days: 23

View full company profile