Senior AI Engineer

Octus • New York, NY

11d

About The Position

As a Senior AI Engineer focused on CreditAI, our flagship GenAI product, you will own complex technical problems across the full AI stack — designing distributed systems, orchestrating multi-agent workflows, and ensuring production reliability at scale.

Requirements

• Bachelor's or Master's degree in Computer Science, Engineering, or a related technical field (or equivalent practical experience).
• 5+ years of experience as an AI Engineer, Machine Learning Engineer, or applied AI practitioner, with a strong foundation in computer science and algorithms.
• Deep Python expertise with a track record of shipping production systems at scale; strong software engineering practices including clean code, testing, code review, and CI/CD.
• Hands-on experience designing, building, and deploying LLM-driven or GenAI applications, including multi-agent architectures and agentic workflows, with familiarity with vector databases, embeddings pipelines, or semantic search systems.
• Hands-on experience designing and implementing automated evaluation frameworks for LLM systems
• Solid understanding of machine learning and applied AI concepts, with the ability to take solutions from prototype to production and translate research ideas into scalable, real-world systems.
• Experience with GPUs for model training or inference, including tuning and deploying open-source deep learning models in production; proficiency with PyTorch or TensorFlow for model development and fine-tuning.
• Practical experience with cloud-based deployments and infrastructure tools (e.g., AWS, Docker, GitHub) and an understanding of modern DevOps practices, containerization, orchestration, and caching strategies.
• Strong problem-solving and systems thinking, with the ability to balance trade-offs across model quality, scalability, inference latency, and cost.
• Excellent communication and collaboration skills, with experience working closely with product managers, engineers, and domain experts to deliver actionable technical solutions.
• Strong ownership and initiative, with the ability to independently drive projects from problem definition to delivery; a passion for learning and staying current with the rapidly evolving AI/ML landscape.

Responsibilities

• Design and implement multi-agent and agentic orchestration frameworks using agent SDKs such as the Claude Agent SDK, Google ADK, or AWS AgentCore, incorporating tools, external data sources, memory, and state management
• Build and maintain MCP servers and integrations to extend AI system capabilities with structured tool use and external context
• Build and optimize RAG pipelines including embedding strategies, vector database, retrieval quality tuning, and cost-aware ingestion design
• Integrate with managed LLM services across cloud providers to support diverse deployment and cost optimization strategies.
• Fine-tune, optimize, and deploy open-source deep learning models for production use cases, leveraging GPU infrastructure for training and inference
• Apply systems thinking to design and optimize AI and LLM systems, balancing quality, scalability, latency, cost, and operational complexity, while implementing efficiency improvements using model selection, prompt design, batching, caching, and retrieval strategies.
• Design and implement automated evaluation frameworks to assess LLM system quality, accuracy, and performance across production workloads
• Apply reinforcement learning techniques (e.g., RLHF, RLAIF) to improve model alignment and task-specific performance
• Architect and manage high-throughput, real-time data pipelines using Kafka
• Design, deploy, and scale production AI services on AWS (Batch, Lambda, ECS, S3, etc), applying modern containerization, CI/CD, and infrastructure-as-code practices
• Implement comprehensive observability frameworks using Datadog — tracking token usage, pipeline latency, error rates, consumer lag, and model performance with actionable alerting
• Identify and resolve production bottlenecks across distributed systems, including database query optimization, consumer scaling, and LLM throughput tuning
• Apply strong problem-solving and critical thinking skills to break down complex, ambiguous requirements into clear, implementable technical components and system designs.
• Conduct code reviews; contribute to team standards around reliability, testing, and operational excellence
• Communicate progress, trade-offs, and outcomes to relevant stakeholders.
• Continuously learn and adapt to advancements in NLP and Generative AI to ensure solutions remain innovative and effective.

Benefits

• Octus employees enjoy competitive health benefits, matched 401k and pension plans, PTO, generous parental leave, gym subsidies, educational reimbursements for career development, recognition programs, pet-friendly offices (US only), and much more.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level