About Us We are building an AI-native platform focused on intelligent automation and privacy-aware AI workflows. Our systems combine LLM reasoning, agent orchestration, multimodal understanding, and structured ML techniques to enable reliable enterprise AI execution at scale.About the Role We are looking for a senior ML Lead with strong hands-on experience in Agentic AI systems, LLM orchestration, and autonomous workflow design. This is a deeply technical, hands-on leadership role. You will design and build autonomous AI engines capable of executing complex tasks with minimal to zero manual intervention, while ensuring reliability, determinism, and performance at scale. We value strong engineering fundamentals (6+ years) along with 2+ years of production experience working with LLMs and agent-based systems.What You’ll Build ·Advanced prompt engineering systems enabling LLMs to: oPerform complex multi-step reasoning oStrictly adhere to defined output schemas oExecute structured decision logic ·Fully autonomous agent systems capable of completing tasks with zero manual intervention ·Dynamic system-prompt construction engines that adapt prompts in real-time based on user input and context ·Multi-agent orchestration frameworks with: oTool calling oMemory management oReasoning chains oPlanner –executor architectures ·Mechanisms to control LLM unpredictability and inconsistent behavior through: oGuardrails oOutput validation layers oDeterministic prompting strategies oSelf- reflection / critique loops oEvaluation pipelines ·Intelligent ingestion and structured understanding of complex, heterogeneous data sources across multiple formats and modalities ·Robust multilingual AI pipelines capable of reasoning and executing tasks across diverse languages and regional contexts ·Advanced data transformation and controlled data generation frameworks for testing, validation, and system robustness ·High-performance inference pipelines using: oOpen-source LLMs and reasoning models oGPU-optimized workloads oBatch inference and parallel execution strategies oScalable architectures for high-throughput AI executionKey Responsibilities ·Architect and lead development of production-grade Agentic AI systems ·Design advanced prompt engineering frameworks for complex task execution ·Build autonomous AI engines with dynamic system prompt generation ·Develop strategies to mitigate hallucination and model inconsistency ·Design multimodal ingestion pipelines for structured extraction and reasoning ·Enable multilingual AI reasoning capabilities across workflows ·Design synthetic and transformation-based data pipelines to improve evaluation coverage and system generalization ·Integrate open-source LLMs and reasoning models into scalable pipelines ·Optimizeinference performance using GPU acceleration and distributed systems ·Design evaluation frameworks to measure reasoning quality, determinism, and reliability ·Own the ML layer architecture and long-term AI roadmap ·Mentor engineers on LLM best practices, agent design patterns, and AI reliabilityWhat We’re Looking For – Required ·6+ years overall software/ML engineering experience ·2+ years hands-on experience building LLM-powered systems in production ·Strong experience building autonomous agent-based systems ·Deepexpertise in prompt engineering for structured, deterministic outputs ·Experience designing dynamic prompt construction pipelines ·Experience handling LLM unpredictability and improving response consistency ·Strong knowledge of: oEmbeddings and vector databases oRAG architectures oPlanner –executor agent models oMemory-augmented agents ·Experience designing structured extraction pipelines across complex document types and semi-structured data ·Experience working with multilingual models and cross-language reasoning systems ·Experience building controlled data generation or transformation systems for robustness testing ·Experience working with open-source LLMs and reasoning models ·Strong Python and backend system design skills ·Experienceoptimizing ML workloads for GPU-based high-throughput inference ·Knowledge of distributed systems and scalable inference architecturesNice to Have ·Experience building privacy- or security-aware AI systems ·Exposure to compliance frameworks (GDPR, HIPAA) ·Experience fine-tuning LLMs or training domain-specific models ·Experience designing model evaluation benchmarks and automated regression testing ·Experience working with multimodal or vision-language modelsWhat You’ll Gain ·Ownership of next-generation autonomous AI systems ·Opportunity to design and scale enterprise-grade Agentic AI from the ground up ·Direct collaboration with founders and senior engineering leaders ·Budget and freedom to experiment with emerging AI models and architectures ·Ability to build real-world, production AI systems that solve complex enterprise problemsCompensation & Benefits ·Competitive senior-level compensation ·Flexible work culture ·Research & experimentation budget for AI innovation
Job Title
Machine Learning Lead – Agentic AI Systems