About NavaSys & the Role
At NavaSys, AI engineers are not just model builderstheyre end-to-end system owners who make AI real in production.
AI Engineer – GenAI, Agentic AI & MLOps
- Build and deploy ML and Generative AI systems into production
- Design and orchestrate agentic AI workflows using modern frameworks
- Help define the engineering culture, tools and patterns for AI across NavaSys
You’ll be part of a tight, high-calibre team that values clean engineering, experimentation and real-world outcomes.
Key Responsibilities
- Design, develop and deploy machine learning and generative AI models into production environments.
- Build and integrate agentic AI systems—intelligent agents capable of reasoning, planning and multi-step decision-making.
- Develop and maintain data pipelines and MLOps workflows using Databricks, MLflow and cloud-native tooling.
- Integrate LLMs and AI agents with external APIs, databases and tools using frameworks such as LangChain, AutoGen, CrewAI, Semantic Kernel, LangGraph.
- Implement and manage Model Context Protocol (MCP) connections between AI agents and enterprise systems.
- Optimize AI workloads on AWS, Azure or GCP, ensuring they are performant, scalable, secure and cost-effective.
- Work with data, cloud and product teams to translate ideas into production-grade AI solutions rather than one-off POCs.
- Ensure security, observability, explainability and governance are first-class citizens in all AI systems you build.
Core Skills
- AI/ML Engineer
- Python
- Machine Learning Engineer
- LLM
- LangChain
- MLflow
- MLOps
Must-Have Capabilities
AI / ML & Data Science
- Strong foundations in machine learning, deep learning and data science.
- Expertise in Python and ML libraries: PyTorch, TensorFlow, scikit-learn, pandas, NumPy.
- Understanding of model evaluation, feature engineering and transfer learning.
- Experience working with vector databases like FAISS, Pinecone, ChromaDB.
Generative AI & NLP
- Hands-on experience with LLMs, prompt engineering, RAG (Retrieval-Augmented Generation) and fine-tuning.
- Familiarity with frameworks such as LangChain, LlamaIndex or similar orchestration tools.
- Experience implementing text generation, summarization, classification and document Q&A systems.
Agentic AI, Agent Frameworks & MCP
- Strong understanding of agentic AI architectures (autonomous agents, tool use, planning, multi-step reasoning).
- Practical experience building AI agents using LangChain, AutoGen, CrewAI, LangGraph, Semantic Kernel or equivalent frameworks.
- Experience designing multi-agent collaboration and task orchestration.
- Hands-on experience with Model Context Protocol (MCP) for secure, robust tool invocation and context sharing.
- Awareness of safety, governance, auditability and agent evaluation frameworks.
Databricks, MLOps & Data Engineering
- Solid experience with Databricks (Spark, Delta Lake, MLflow, feature store).
- End-to-end work on data pipelines, ETL/ELT and real-time streaming.
- Proficiency in MLOps best practices: model registry, versioning, drift detection, rollbacks.
- Experience implementing observability and automation for ML systems in production.
Cloud & Infrastructure
- Hands-on experience deploying AI workloads on AWS, Azure or GCP.
- Familiarity with SageMaker, Azure ML or Vertex AI.
- Experience with Docker, Kubernetes and serverless paradigms.
- Working knowledge of Infrastructure as Code (Terraform / CloudFormation) and CI/CD pipelines.
Software Engineering & APIs
- Strong software engineering fundamentals and coding discipline.
- Experience building REST / GraphQL APIs and microservices.
- Understanding of event-driven and asynchronous architectures (Kafka, Pub/Sub, message queues).
- Experience integrating AI components with existing enterprise systems.
Security, Observability & Responsible AI
- Knowledge of monitoring, logging and tracing (Prometheus, Grafana, OpenTelemetry).
- Experience implementing secure AI practices (RBAC, secret management, prompt injection defenses).
- Understanding of model explainability, bias mitigation and ethical AI considerations.
Nice-to-Have
- Familiarity with reinforcement learning and planning-based agents.
- Experience with knowledge graphs and symbolic reasoning.
- Exposure to multi-modal agents (text + vision + audio).
- Contributions to open-source AI or agent frameworks.
- Experience with edge or on-device AI.
- Certifications in Cloud AI / MLOps / Databricks / GenAI.
