Auxo AI - Senior Applied AI Engineer - AI Agents

AuxoAI is hiring a Senior Applied AI Engineer to build and deploy production-grade AI agents for structured reasoning, planning and decision-making. The systems combine LLM-based reasoning with classical planning, search and optimization to support autonomous workflows, decision engines and tool-driven applications. The role is listed for Bangalore, Hyderabad, Mumbai and Gurgaon/Gurugram, India. The posting specifies 3–8 years of experience, full-time employment and a bachelor’s degree in its structured job data.

Responsibilities

• Architect modular agent frameworks with skill decomposition, tool orchestration and persistent state tracking. Experiment with machine learning, graph algorithms and classical AI approaches where existing architectures are insufficient.
• Implement planning and search methods, including Monte Carlo Tree Search, beam search, A search, heuristic search and graph-based planning. Design decision loops that balance exploration against exploitation, cost against accuracy, and latency against reasoning depth.
• Build episodic, semantic and vector-based memory with effective retrieval. Develop tool-calling systems with execution validation, retries and failure recovery.
• Evaluate agents using task-success metrics, rollout simulations and multi-sample validation. Improve performance through distillation, synthetic trajectory generation, prompt compression and context pruning.
• Deliver reliable, observable production systems that meet cost, throughput, latency and limited-context constraints.

Required qualifications

• Strong experience implementing search or planning algorithms beyond basic use cases, including tree search or heuristic planning; hands-on experience with Monte Carlo Tree Search or related decision-making frameworks.
• Understanding of state-space representations, heuristic design and decision trade-offs. Experience building or substantially customizing real-world agent frameworks and designing tool-use or function-calling architectures under practical constraints.
• Strong Python engineering skills focused on scalable, reliable systems.

Preferred qualifications

• Experience with reinforcement learning methods such as policy gradients, value estimation or reward modeling; multi-agent systems; agent robustness evaluations; LLM inference optimization for latency, throughput and cost; or distributed task orchestration and large-scale AI workflows.