Company Description
Daice Labs is building hybrid AI frameworks that integrate today's models into systems that learn continuously. Founded by MIT CSAIL scientists, we focus on building new architectures by combining LLMs/DL with symbolic reasoning and bio-inspired system design. Operating on two tracks, our Product Lab develops industry-specific solutions for collaborative human teams + AI co-building and co-owning vertical applications, while our Research Lab explores how principles of natural intelligence can guide systems design of new hybrid AI architectures.
Join us in taking the next leap in productivity through collaborative innovation.
Role Description
This is a full-time remote role for a Junior AI Engineer focused on Inference & Platform Integration. The engineer will be responsible for deploying, optimizing, and scaling AI/ML models in production environments, with emphasis on inference performance and seamless platform integration. Day-to-day tasks include implementing efficient inference pipelines, integrating models into existing systems and APIs, monitoring model performance in production, and collaborating with research teams to operationalize cutting-edge AI solutions. The engineer will bridge the gap between research innovation and production deployment, ensuring our hybrid AI systems run reliably at scale.
Qualifications:
- Strong understanding of ML inference optimization techniques (quantization, distillation, batching, caching)
- Experience with inference frameworks and runtimes (ONNX, TensorRT, vLLM, TGI, or similar)
- Proficiency in Python and TypeScript; familiarity with Go is a plus
- Solid grasp of LLMs, neural networks, and agentic architectures in production contexts
- 1-2 years building ML platforms, deployment pipelines, or developer tools
- Experience with API design and implementation
- Knowledge of containerization (Docker, Kubernetes) and WASM sandboxing
- Hands-on experience with model serving infrastructure and orchestration systems
- Observability and monitoring (OpenTelemetry, Prometheus, or similar)
- Database experience and message queues
- Understanding of resource management: quotas, rate limiting, autoscaling
- Security-conscious approach: network policies, authentication, PII handling, audit logging
- Evaluation mindset: experience building test suites, regression tests, or performance benchmarks for ML systems
- Familiarity with model versioning, deployment gates, rollback strategies
- Performance monitoring and drift detection practices
- Experience with hybrid AI architectures or multi-model orchestration
- Background in bio-inspired system design principles
- Knowledge of signing/SBOMs and supply chain security
- Experience with least-privilege patterns and zero-trust architectures
- Excellent problem-solving abilities and collaborative work style
- Strong written and verbal communication skills
- Ability to work independently and remotely
- Bachelor's degree in Computer Science, AI, Machine Learning, Engineering, or related field
Retry
