AuxoAI is hiring a Senior AI Engineer to design and deploy production-grade AI agents capable of structured reasoning, planning, and decision-making.

This role focuses on building intelligent agent systems and predictive ML solutions that power real-world enterprise workflows — going well beyond chatbot or RAG-style application development. The ideal candidate will design AI architectures that combine LLM-based reasoning with classical ML techniques, operating reliably in production environments with constraints around latency, cost, data quality, and enterprise system integration.

You will work on advanced AI systems that power autonomous workflows, decision engines, and tool-driven agent ecosystems — spanning use cases in manufacturing, finance, supply chain, and enterprise operations.

You will also work on problems where existing architectures may not be sufficient and will be expected to experiment with new approaches that combine large language models, machine learning models, and data engineering patterns to build reliable, production-grade systems

Location - Mumbai/Bangalore/Hyderabad/Gurgaon (Hybrid - 3 Days a week in Office)

Responsibilities:

Design and architect modular AI agent frameworks incorporating skill decomposition, tool orchestration, and persistent state tracking.

Build and deploy supervised and unsupervised ML models for prediction, classification, anomaly detection, and pattern recognition tasks in production environments.

Develop decision-making loops that balance trade-offs between exploration vs. exploitation, cost vs. accuracy, and latency vs. reasoning depth.

Build structured memory systems including episodic memory stores, semantic memory layers, and vector-based memory with optimised retrieval strategies.

Design tool-calling architectures with strong execution validation, retry mechanisms, and failure recovery strategies.

Develop evaluation frameworks to measure agent and model performance using task success metrics, rollout simulations, model accuracy benchmarks, and multi-sample validation approaches.

Integrate AI agents and ML models with enterprise systems.

Deliver production-ready AI systems that meet operational requirements around reliability, cost efficiency, throughput, observability, and enterprise security standards.

Requirements

3-7 years of experience building machine learning or AI systems in production environments.

Hands-on experience training, evaluating, and deploying ML models using frameworks such as scikit-learn, XGBoost, or PyTorch — including feature engineering, cross-validation, and model monitoring in production.

Strong experience building or extensively customising agent frameworks for real-world applications.

Hands-on experience designing tool-use or function-calling architectures under practical system constraints.

Experience working with cloud-native AI platforms, preferably GCP Vertex AI and Gemini, including model deployment, endpoint management, and AI pipeline orchestration.

Experience integrating AI solutions with enterprise data systems — ERP APIs, data lakehouses (Databricks), or industrial data sources (MES, IoT/sensor streams).

Strong understanding of RAG architectures, vector databases, and retrieval strategies — with the ability to go beyond retrieval into agentic reasoning and action.

Strong Python engineering skills with a focus on scalable, reliable, and maintainable system design.

Candidates whose primary experience is limited to RAG pipelines or prompt engineering without hands-on ML model development or production agent delivery may not be a strong fit for this role.

Nice to Have

Experience with reinforcement learning techniques such as policy gradients, value estimation, or reward modeling.

Experience building multi-agent or collaborative agent systems.

Experience designing evaluation frameworks for agent robustness and reliability.

Experience optimising LLM inference pipelines for latency, throughput, and cost efficiency.

Familiarity with MLOps practices including model versioning, drift monitoring, retraining pipelines, and model registries.

Familiarity with distributed task orchestration systems and large-scale AI workflow management.

Note: Given the urgency of the role, we are currently prioritizing candidates who can join immediately or within 2 weeks.

Habilidades requeridas

AI agent framework design and customizationAI architecture design combining LLM-based reasoning with classical MLSupervised and unsupervised ML model training, evaluation, and deployment (scikit-learn, XGBoost, PyTorch; feature engineering, cross-validation, monitoring)Delivery of production-grade AI systems meeting reliability, cost-efficiency, throughput, observability, and enterprise security requirementsDesigning tool-calling/function-calling architectures with execution validation, retry mechanisms, and failure recoveryDesigning structured memory systems (episodic memory, semantic layers, vector-based memory) and optimized retrieval strategiesDesigning decision-making loops that balance exploration vs. exploitation, cost vs. accuracy, and latency vs. reasoning depthRAG architectures, vector databases, and retrieval strategies with agentic reasoning and action beyond retrievalCloud-native AI platform experience (GCP Vertex AI, Gemini) including model deployment, endpoint management, and pipeline orchestrationIntegration of AI/ML solutions with enterprise data systems (ERP APIs, Databricks/data lakehouses, MES, IoT/sensor streams)Strong Python engineering for scalable, reliable, and maintainable system designDesigning evaluation frameworks for agent and model performance (task success metrics, rollout simulations, model accuracy benchmarks, multi-sample validation)MLOps practices (model versioning, drift monitoring, retraining pipelines, model registries)Reinforcement learning techniques (policy gradients, value estimation, reward modeling)

Empleos similares